© 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. 1862
    Prev
    Next
    INDEX
    Explanations

    script interpreter declarations

    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
     issues
    -0.84
     opinions
    -0.77
     thoughts
    -0.77
    が付
    -0.77
     Supp
    -0.77
    讃
    -0.75
    ToUpper
    -0.74
    取締
    -0.73
     main
    -0.72
     slipping
    -0.70
    POSITIVE LOGITS
    env
    1.52
     env
    0.86
     ENVIRONMENTAL
    0.85
     environmental
    0.85
     Cellar
    0.83
     liek
    0.82
    nikom
    0.82
     menuItem
    0.82
    نر
    0.81
    촨
    0.81
    Activations Density 0.013%

    No Known Activations