© 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. 66188
    Prev
    Next
    INDEX
    Explanations

    investigation or murder

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

    security and observation

    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
    š
    0.56
    uš
    0.49
    é
    0.49
    č
    0.49
    rš
    0.48
    ,
    0.48
    voje
    0.47
    ,\,
    0.47
    q
    0.47
    ő
    0.47
    POSITIVE LOGITS
     पुरंदरे
    0.53
     Règles
    0.50
     الرج
    0.48
     Turnover
    0.47
    事故
    0.46
     Suprema
    0.46
    िसोदिया
    0.46
    ຈາກ
    0.45
     Crystall
    0.45
    栆
    0.45
    Activations Density 0.001%

    No Known Activations