© 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. 59045
    Prev
    Next
    INDEX
    Explanations

    section headers, file starts

    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
     transgress
    -0.69
     declaratory
    -0.67
    ೈ
    -0.65
     shaved
    -0.65
    尙
    -0.64
    现实
    -0.63
    urazione
    -0.63
     Vig
    -0.63
    зраст
    -0.62
    ccd
    -0.61
    POSITIVE LOGITS
    acri
    0.71
    Uart
    0.69
     text
    0.68
    았
    0.65
     Ack
    0.64
    ټ
    0.63
     گری
    0.63
    ValueChanged
    0.63
     regra
    0.63
    дование
    0.62
    Activations Density 0.076%

    No Known Activations