© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 150786
    Prev
    Next
    INDEX
    Explanations

    transaction, project, term, cause, system, flamingo, candidate

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

    area itself, monitoring public

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     Indy
    0.50
    indy
    0.44
     Skipper
    0.43
    ໌
    0.42
     Ela
    0.42
    etten
    0.42
     your
    0.42
     conceding
    0.42
     Hole
    0.41
     Ángel
    0.41
    POSITIVE LOGITS
    お得
    0.51
    כ
    0.51
     نہيں
    0.50
     வாக
    0.49
    +}$,
    0.49
    寸法
    0.49
     கூடுதலாக
    0.48
    ACTIONS
    0.47
    となる
    0.46
    ﹰ
    0.46
    Activations Density 0.000%

    No Known Activations