© 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. 24-GEMMASCOPE-2-RES-16K
    7. 7372
    Prev
    Next
    INDEX
    Explanations

    import and use statements

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

    This neuron strongly activates on structural/formatting tokens—especially the '<' symbol and similar markup or punctuation delimiters.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
    ว
    0.71
    τηση
    0.66
    匚
    0.66
    Ԁ
    0.64
     proposent
    0.63
    efeated
    0.61
     ৃ
    0.61
    LaunchScheme
    0.60
    пени
    0.60
     deprecated
    0.60
    POSITIVE LOGITS
     prenda
    0.65
     irregularity
    0.62
    Others
    0.62
    आधी
    0.62
    सर्व
    0.61
    扱い
    0.61
    Berger
    0.61
    Vé
    0.60
    埃
    0.60
     emboss
    0.59
    Activations Density 0.000%

    No Known Activations