© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 50783
    Prev
    Next
    INDEX
    Explanations

    diagram and wiring

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

    exoskeleton, breathed, Consumer, vectors, annually, needs

    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
     you
    0.54
     occurrence
    0.50
    double
    0.50
    1
    0.48
     were
    0.48
     occurrences
    0.48
     us
    0.47
     double
    0.46
    f
    0.46
     taking
    0.45
    POSITIVE LOGITS
    纮
    0.55
    ເຮ
    0.47
     필요
    0.46
     灯
    0.46
    名を
    0.46
    aparikkh
    0.45
    ઓ
    0.44
    학
    0.44
    robespierre
    0.44
    乃至
    0.43
    Activations Density 0.000%

    No Known Activations