© 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. 69178
    Prev
    Next
    INDEX
    Explanations

    cookies and session information

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

    session configuration and secrets

    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
     FEBRUARY
    0.57
     "@
    0.54
     JANUARY
    0.53
     REGIUNI
    0.52
     கூட்ட
    0.51
     सामन्या
    0.51
     };
    0.49
     दहा
    0.49
     ศ
    0.48
     REQUEST
    0.48
    POSITIVE LOGITS
     bushing
    0.46
    '
    0.46
    inl
    0.43
    /
    0.43
    两次
    0.43
    imide
    0.43
    ia
    0.42
    yle
    0.42
    ί
    0.42
     chicks
    0.42
    Activations Density 0.000%

    No Known Activations