© 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. 102655
    Prev
    Next
    INDEX
    Explanations

    roles or characters in media

    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
     hobbit
    -0.92
    colazione
    -0.79
     incurred
    -0.79
    Jimin
    -0.78
     Mark
    -0.77
    getConnection
    -0.74
    uxxxx
    -0.74
    veline
    -0.73
     recorded
    -0.73
    uVar
    -0.73
    POSITIVE LOGITS
    Mayor
    1.04
     Mayor
    1.04
    Professor
    0.99
    heed
    0.91
     Большой
    0.90
    professor
    0.89
     Professor
    0.87
    ceton
    0.86
    );;
    0.84
    mayor
    0.82
    Activations Density 0.026%

    No Known Activations