© 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. 2064
    Prev
    Next
    INDEX
    Explanations

    technical terms and their uses

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

    programming and data libraries

    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
     colossal
    0.49
     vehement
    0.48
     sentimento
    0.47
    <unused55>
    0.46
    <unused9>
    0.46
     domicilio
    0.46
    <unused85>
    0.45
     apprehensive
    0.45
     stargazerCount
    0.45
    蒞
    0.45
    POSITIVE LOGITS
    或其他
    0.63
    Simple
    0.60
    可以
    0.59
    を使って
    0.58
    做一个
    0.58
    を使う
    0.57
    可以让
    0.57
    Create
    0.57
    Use
    0.56
    Using
    0.55
    Activations Density 0.064%

    No Known Activations