© 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. 11676
    Prev
    Next
    INDEX
    Explanations

    Formatting tags or names

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

    bold formatting

    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
    นิด
    0.85
    </em>
    0.84
    ahas
    0.82
    ą
    0.77
    นอก
    0.77
    น้อง
    0.75
    ется
    0.72
     habíamos
    0.72
    близи
    0.72
    </strong>
    0.71
    POSITIVE LOGITS
    i
    0.91
    在
    0.90
     في
    0.86
    U
    0.84
    도
    0.82
    もら
    0.82
    ᆯ
    0.78
    j
    0.77
     در
    0.76
    ও
    0.75
    Activations Density 0.000%

    No Known Activations