© 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. 6175
    Prev
    Next
    INDEX
    Explanations

    names after punctuation

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

    The neuron is especially sensitive to verbs that denote key events or actions (e.g. “immigrated,” “made,” “reminds,” “inspired,” “says,” “shot,” etc.).

    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_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
    ㅠㅠ
    0.79
     Ι
    0.69
    ６
    0.68
    ㅠ
    0.66
    ２
    0.65
    １
    0.63
    ５
    0.63
    ８
    0.62
    ４
    0.61
    assade
    0.60
    POSITIVE LOGITS
     Williams
    0.82
     Evans
    0.80
     Johnson
    0.80
     Zuckerberg
    0.79
     Michaels
    0.79
     Adams
    0.78
     Schwarzenegger
    0.78
     Mr
    0.75
     Jones
    0.74
     Jacobs
    0.74
    Activations Density 0.795%

    No Known Activations