© 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. 129320
    Prev
    Next
    INDEX
    Explanations

    backup for client or weight

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

    introduces concepts or definitions

    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
    ك
    0.68
    تال
    0.57
    ال
    0.56
    تالي
    0.52
     Saunders
    0.52
     ბ
    0.51
    Ầ
    0.51
    ت
    0.50
     our
    0.50
     Lowe
    0.50
    POSITIVE LOGITS
     cumulative
    0.46
    ष्णु
    0.45
    enthic
    0.45
    chtig
    0.44
     photometric
    0.44
    cumulative
    0.44
    irent
    0.43
    reform
    0.43
     probationary
    0.43
    sted
    0.43
    Activations Density 0.001%

    No Known Activations