© 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. 75101
    Prev
    Next
    INDEX
    Explanations

    review and change

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

    function definition or initial state

    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
    City
    0.51
    righteous
    0.50
    உங்கள்
    0.49
    ￡
    0.49
     lounging
    0.48
    att
    0.47
    edition
    0.46
    เมือง
    0.46
     เมือง
    0.46
    क्षम
    0.46
    POSITIVE LOGITS
     coprodu
    0.43
    팠
    0.42
     využ
    0.41
     Alfvén
    0.40
    زمت
    0.40
    azoo
    0.40
    putchar
    0.40
     singers
    0.40
    ングル
    0.40
     xyz
    0.39
    Activations Density 0.001%

    No Known Activations