© 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. 87007
    Prev
    Next
    INDEX
    Explanations

    fitting session and visits

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

    presenting different viewpoints

    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
    ombrie
    0.47
    cmake
    0.47
    मानी
    0.46
    isasi
    0.46
     கற்க
    0.45
     индекс
    0.45
     말투
    0.45
     板
    0.45
     தோட்டங்கள்
    0.45
    reads
    0.44
    POSITIVE LOGITS
     oppure
    0.47
     u
    0.45
    امد
    0.42
     o
    0.41
     dick
    0.41
     a
    0.40
     runner
    0.40
     بالکل
    0.39
    বর্ধ
    0.39
    夜
    0.38
    Activations Density 0.000%

    No Known Activations