© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 67979
    Prev
    Next
    INDEX
    Explanations

    names followed by suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     and
    -1.11
     questi
    -1.09
     かな
    -1.07
    和
    -1.04
     sebagai
    -1.02
    ⁠
    -1.00
    そして
    -0.97
     doua
    -0.97
    */
    
    -0.95
    当
    -0.93
    POSITIVE LOGITS
     from
    2.19
     từ
    1.10
    Also
    1.07
    mochila
    1.00
     llanto
    0.99
    ブログ村
    0.99
     Projektu
    0.98
    鎶
    0.98
     Konkur
    0.94
     väljer
    0.93
    Activations Density 0.045%

    No Known Activations