© 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. 58874
    Prev
    Next
    INDEX
    Explanations

    code and template 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
     llegaron
    -0.88
     these
    -0.84
     isEqualToString
    -0.81
    ələ
    -0.80
     to
    -0.76
     penumpang
    -0.76
    եր
    -0.75
    اما
    -0.73
    randomUUID
    -0.73
     those
    -0.72
    POSITIVE LOGITS
    loop
    1.05
     RELATIONSHIP
    0.97
     ihan
    0.91
     depósitos
    0.90
     loop
    0.88
    ujeme
    0.87
    izacin
    0.85
    ૯
    0.84
     errors
    0.84
    ända
    0.84
    Activations Density 0.015%

    No Known Activations