© 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. 196902
    Prev
    Next
    INDEX
    Explanations

    attacker, rage, games, monthly

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

    specialized contractor, hourly rate, mechanism

    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
    рованные
    0.44
    ваш
    0.44
     ૩
    0.44
    ра
    0.43
     куро
    0.43
    два
    0.42
    設定
    0.42
     Jew
    0.42
     diving
    0.42
     немного
    0.41
    POSITIVE LOGITS
    、$
    0.54
    ，
    0.47
    ={()
    0.47
     induc
    0.46
    ্থিত
    0.46
    cssMode
    0.45
    、（
    0.45
     ()
    0.44
     inducement
    0.44
    ,((
    0.44
    Activations Density 0.001%

    No Known Activations