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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 34614
    Prev
    Next
    INDEX
    Explanations

    Scott followed by name or title

    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
    on
    -3.39
    *
    -2.94
    ↵↵
    -2.83
    or
    -2.45
     
    -2.42
    \\
    -2.33
    and
    -2.23
    {
    -2.14
     but
    -2.13
    s
    -2.13
    POSITIVE LOGITS
    𖤣
    3.42
    
    3.06
    guigu
    3.00
     nacionais
    2.83
     pessoais
    2.69
     adicionais
    2.61
    諴
    2.58
    鍇
    2.56
     legais
    2.53
     gerais
    2.53
    Activations Density 0.018%

    No Known Activations