© 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. 205781
    Prev
    Next
    INDEX
    Explanations

    documented information

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

    `*` placeholder and list replacement

    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
    Negative Logits
     സിനിമ
    0.49
    EY
    0.46
    SO
    0.46
    Directors
    0.45
    TER
    0.45
    煒
    0.45
    DF
    0.44
    DC
    0.44
    GPU
    0.44
    Gotham
    0.44
    POSITIVE LOGITS
     substantiated
    0.49
     ngunit
    0.46
     intraven
    0.45
    ات
    0.45
     Bahkan
    0.44
     esboço
    0.44
    ında
    0.43
    ක්ෂ
    0.43
     عرضه
    0.43
    ில்
    0.43
    Activations Density 0.001%

    No Known Activations