© 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. 19325
    Prev
    Next
    INDEX
    Explanations

    public domain, period

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

    determine, attempts, license

    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
    ۔
    0.56
     Failed
    0.54
     顔
    0.54
     말했다
    0.54
     Interviews
    0.52
     quét
    0.51
     Helped
    0.50
     Updated
    0.50
    )】
    0.50
     Backup
    0.49
    POSITIVE LOGITS
    ва
    0.58
    o
    0.52
    in
    0.52
    inform
    0.51
    н
    0.51
    et
    0.50
    rural
    0.50
    unknown
    0.50
    maximum
    0.49
    alunos
    0.49
    Activations Density 0.000%

    No Known Activations