© 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. 61406
    Prev
    Next
    INDEX
    Explanations

    dates and stages

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

    list separators and specific timings

    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
     കോണ്‍
    0.53
    ⣤
    0.52
     underweight
    0.50
    ("\(
    0.50
     zw
    0.47
    Fract
    0.46
     Displaystyle
    0.45
     मिळाल
    0.45
    ,",
    0.45
    滩
    0.44
    POSITIVE LOGITS
    uš
    0.54
    lüssel
    0.52
    ous
    0.52
    ci
    0.47
    tiin
    0.47
    ves
    0.47
    akar
    0.47
    lis
    0.47
    vej
    0.46
    notas
    0.46
    Activations Density 0.000%

    No Known Activations