© 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. 49274
    Prev
    Next
    INDEX
    Explanations

    cancel reply

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

    user cancelling operations

    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
     (
    0.67
     ,
    0.57
    ,
    0.54
     [(
    0.52
     in
    0.52
    ],
    0.49
     acknowledges
    0.49
    ),
    0.47
    ”,
    0.46
     вследствие
    0.45
    POSITIVE LOGITS
    ვით
    0.52
    コマンド
    0.51
    重大
    0.50
    forderung
    0.49
    ޏ
    0.48
    طرف
    0.46
    プログラム
    0.45
    بس
    0.45
    னே
    0.44
    phpunit
    0.44
    Activations Density 0.001%

    No Known Activations