© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65267
    Prev
    Next
    INDEX
    Explanations

    label definition

    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
    
    -0.92
    図
    -0.88
     gestes
    -0.85
    whelming
    -0.83
    /).
    -0.82
     Iglesias
    -0.80
     comigo
    -0.77
     áo
    -0.77
     ließ
    -0.77
    absence
    -0.77
    POSITIVE LOGITS
     victor
    0.88
    那我
    0.84
    blocks
    0.81
    Москва
    0.81
     glutton
    0.79
    vlá
    0.79
    InternalFrame
    0.78
    我很
    0.78
    ++){
    0.77
    거나
    0.76
    Activations Density 0.000%

    No Known Activations