© 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. 2909
    Prev
    Next
    INDEX
    Explanations

    build query syntax

    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
     poign
    -0.88
     Trolley
    -0.81
     SILVER
    -0.79
     Imma
    -0.78
    ENCIA
    -0.78
    ERK
    -0.77
     PLN
    -0.77
     Boun
    -0.77
     Agra
    -0.77
     للف
    -0.76
    POSITIVE LOGITS
     você
    0.89
    guitarra
    0.87
    орк
    0.85
    SearchTree
    0.82
    ksessa
    0.77
    acked
    0.77
    ClientRect
    0.76
    melde
    0.76
    路上
    0.75
    гән
    0.75
    Activations Density 0.010%

    No Known Activations