© 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. 115128
    Prev
    Next
    INDEX
    Explanations

    to verb

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

    someone who, risking life, designed to, raising children

    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
    䓶
    0.48
     vVertex
    0.47
    䈤
    0.46
     विटामिन
    0.46
    争议
    0.45
    ศึกษา
    0.44
     वेरिएबल
    0.44
    บ้าน
    0.44
    事务所
    0.43
    בית
    0.43
    POSITIVE LOGITS
    igious
    0.53
    person
    0.49
    inely
    0.49
    in
    0.48
    on
    0.48
    .
    0.47
    ot
    0.47
    ter
    0.47
    '
    0.47
    we
    0.47
    Activations Density 0.000%

    No Known Activations