© 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. 33629
    Prev
    Next
    INDEX
    Explanations

    code structure and types

    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
    endlich
    -0.79
     kertoo
    -0.78
     beslut
    -0.78
     Bedürfnisse
    -0.77
    tivo
    -0.73
    unexpected
    -0.71
    ashir
    -0.71
    Pinned
    -0.71
    イレ
    -0.70
    texas
    -0.70
    POSITIVE LOGITS
    int
    1.23
     LL
    0.92
     AMERIC
    0.89
    register
    0.88
    static
    0.88
    LL
    0.88
     friend
    0.88
    bool
    0.88
    ll
    0.86
     priority
    0.84
    Activations Density 0.004%

    No Known Activations