© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98304
    Prev
    Next
    INDEX
    Explanations

    free software GNU GPL

    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
     Components
    -0.86
     DOUGLAS
    -0.85
     BLUE
    -0.81
    arrhea
    -0.81
     Inn
    -0.81
    iowa
    -0.80
    COMPONENT
    -0.79
     quenched
    -0.79
     attenuated
    -0.79
    шенко
    -0.78
    POSITIVE LOGITS
     Guardian
    0.82
    Guardian
    0.82
     guardian
    0.81
    MEAN
    0.80
    ]++;
    0.75
     quartile
    0.74
    гать
    0.74
    Список
    0.73
    DESCRIPCIÓN
    0.73
     GUARD
    0.73
    Activations Density 0.006%

    No Known Activations