© 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. 120025
    Prev
    Next
    INDEX
    Explanations

    foreign language and abbreviations

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

    conjugations

    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
     Gw
    0.50
     Bedarf
    0.45
     Levy
    0.45
     Libya
    0.44
    瀰
    0.43
     জেলা
    0.43
     gutted
    0.43
     Moot
    0.42
     Alec
    0.42
    제로
    0.42
    POSITIVE LOGITS
    獺
    0.49
    विश्व
    0.49
    Im
    0.49
     العالم
    0.49
     بن
    0.46
    ̯
    0.46
    IK
    0.44
    им
    0.44
     SHRI
    0.44
    Ivoire
    0.44
    Activations Density 0.001%

    No Known Activations