© 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. 137939
    Prev
    Next
    INDEX
    Explanations

    paste or trick

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

    non-english characters or scripts

    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
    是一种
    0.56
    <0xA0>
    0.51
    ค
    0.50
    严
    0.49
     embarazada
    0.49
    一
    0.48
    บ
    0.48
    ෙ
    0.48
     ژان
    0.48
    ร
    0.47
    POSITIVE LOGITS
    SIBILITY
    0.48
    RECTION
    0.46
    ಸೂ
    0.45
     പിന്നെ
    0.44
    RefIn
    0.43
     بقي
    0.42
     設計
    0.42
     کھولنے
    0.41
     Colombe
    0.41
    Rectangle
    0.41
    Activations Density 0.004%

    No Known Activations