© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 37974
    Prev
    Next
    INDEX
    Explanations

    shell commands and file paths

    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_34/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
    ">'.$
    -0.99
    _"+
    -0.90
    /'.$
    -0.88
    ."+
    -0.87
    '+
    -0.82
    NSY
    -0.81
     ६
    -0.81
     solchen
    -0.79
    \"");
    -0.79
    (");
    -0.77
    POSITIVE LOGITS
    <%=
    0.89
    
    0.84
     espir
    0.81
    =@
    0.80
    GetAsync
    0.80
    桥
    0.79
    camiento
    0.76
    ച്ച
    0.76
    ferde
    0.75
     kari
    0.73
    Activations Density 0.089%

    No Known Activations