© 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. 102781
    Prev
    Next
    INDEX
    Explanations

    correctness or choice

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

    sunset caught or reflecting

    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
    🔥
    0.48
     descriptors
    0.45
    assessment
    0.44
    予測
    0.43
    assess
    0.43
     assessment
    0.42
    起点
    0.42
     assessments
    0.42
     occurrences
    0.41
    >');
    0.41
    POSITIVE LOGITS
    টেলে
    0.43
     умень
    0.43
     richtige
    0.42
     Chọn
    0.42
     ಸರಿಯ
    0.42
     richtigen
    0.40
     stabile
    0.39
     lessened
    0.39
    glia
    0.39
     correcta
    0.38
    Activations Density 0.000%

    No Known Activations