© 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. 32222
    Prev
    Next
    INDEX
    Explanations

    dependencies, references, and uses

    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
    útbol
    -0.81
     Nähr
    -0.79
     navide
    -0.78
     Weltkrieg
    -0.77
    aporan
    -0.75
    equalsIgnoreCase
    -0.75
     حض
    -0.74
    amoan
    -0.73
     donned
    -0.73
     znám
    -0.72
    POSITIVE LOGITS
     references
    1.95
     referencing
    1.87
     use
    1.77
     uses
    1.72
     reference
    1.72
     depend
    1.71
     rely
    1.59
    refer
    1.58
     refers
    1.53
    reference
    1.49
    Activations Density 0.311%

    No Known Activations