© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1906
    Prev
    Next
    INDEX
    Explanations

    file paths and extensions

    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
    coating
    -0.82
     Ehe
    -0.82
    inkles
    -0.81
     geladeira
    -0.81
    ската
    -0.79
     pieniądze
    -0.77
     organismes
    -0.77
     внимания
    -0.76
    ेंगे
    -0.75
    eaks
    -0.73
    POSITIVE LOGITS
     Twig
    0.84
     Schae
    0.80
     Sonoma
    0.77
    じん
    0.76
    就业
    0.75
     мона
    0.75
    rceil
    0.74
     orifice
    0.73
     twig
    0.73
     Herman
    0.73
    Activations Density 0.003%

    No Known Activations