© 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. 110538
    Prev
    Next
    INDEX
    Explanations

    category of words

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

    potential benefits and issues

    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
    チャンピオン
    0.47
     militia
    0.47
     чемпионате
    0.46
    يران
    0.46
    貫
    0.45
     ciência
    0.44
     DPRD
    0.44
     करण्या
    0.44
     memória
    0.44
    ॅप
    0.44
    POSITIVE LOGITS
    y
    0.61
    utum
    0.60
    ut
    0.53
    ri
    0.52
    ry
    0.52
    yta
    0.52
    us
    0.51
    estion
    0.51
     موجود
    0.51
    ahun
    0.50
    Activations Density 0.001%

    No Known Activations