© 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. 63608
    Prev
    Next
    INDEX
    Explanations

    Sondheim satirical political films

    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
    elu
    -0.78
    딘
    -0.76
    tamol
    -0.75
    jeg
    -0.74
     osal
    -0.73
     magari
    -0.73
     アート
    -0.72
    booked
    -0.72
    wardship
    -0.72
     jamb
    -0.72
    POSITIVE LOGITS
     Sweeney
    1.03
     Todd
    0.95
     Demon
    0.90
    Todd
    0.87
     pie
    0.82
    weeney
    0.79
     demon
    0.78
    tisserie
    0.77
     Fox
    0.77
     predator
    0.76
    Activations Density 0.020%

    No Known Activations