© 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. 219665
    Prev
    Next
    INDEX
    Explanations

    Openhomethough

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

    VIN, crew, passage, DEN, 3

    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
     벗
    0.47
     scenic
    0.46
    гона
    0.45
     സാഹ
    0.45
    <0x0D>
    0.42
     printemps
    0.42
     gede
    0.41
     funeral
    0.40
     სამ
    0.40
     springtime
    0.40
    POSITIVE LOGITS
     ${(
    0.48
     सिद्धांत
    0.47
    बूझ
    0.46
    iería
    0.45
    iéndose
    0.45
    精确
    0.44
    }/${
    0.43
     automática
    0.43
    颛
    0.43
    bayes
    0.43
    Activations Density 0.001%

    No Known Activations