© 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. 78556
    Prev
    Next
    INDEX
    Explanations

    error handling andregistration information

    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
    的模样
    -0.80
     has
    -0.78
     avez
    -0.76
    []){
    -0.74
     e
    -0.74
     Courtesy
    -0.73
     регу
    -0.71
     творо
    -0.71
    rogates
    -0.69
     Chowdhury
    -0.69
    POSITIVE LOGITS
    Logger
    1.34
     Logger
    1.25
    로그
    0.88
    ex
    0.84
     logger
    0.83
    ORDAN
    0.79
    Reported
    0.79
     Reported
    0.78
     Reporter
    0.77
    Excess
    0.77
    Activations Density 0.002%

    No Known Activations