© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12493
    Prev
    Next
    INDEX
    Explanations

    aroused / arrived / culminated / thanks / outset

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron strongly activates on numerical figures and quantitative statistics (e.g. counts, years, measures).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    words describing successful outcomes or achievements in narratives about accomplishment.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    language signaling successful outcomes, resolutions, victories, or climactic milestones in a narrative or report.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     किंवा
    0.63
     전에
    0.61
     ছাড়াও
    0.61
     इत्यादी
    0.60
    }"/>
    0.58
     केलेली
    0.58
     сейчас
    0.57
     geeft
    0.57
     dà
    0.57
    ":"","
    0.57
    POSITIVE LOGITS
     thanks
    1.06
     puisque
    1.03
    thanks
    0.93
     courtesy
    0.88
     grazie
    0.88
     puisqu
    0.87
     عندما
    0.86
     graças
    0.86
     apabila
    0.85
     gracias
    0.84
    Activations Density 0.215%

    No Known Activations