© 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. 10-GEMMASCOPE-RES-131K
    7. 61493
    Prev
    Next
    INDEX
    Explanations

    SHA256 or OAuth2

    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_10/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
    </h3>
    -2.92
    </i>
    -2.20
    </h1>
    -2.14
    鸶
    -1.96
    这事
    -1.94
    髕
    -1.85
    这件事
    -1.84
     dieses
    -1.78
    ”:
    -1.76
    敍
    -1.73
    POSITIVE LOGITS
    (
    2.06
    In
    1.95
    愎
    1.87
     ſame
    1.80
    SaveChangesAsync
    1.78
     \'
    1.73
     Überras
    1.72
     teilweise
    1.70
    *
    1.69
    假如
    1.67
    Activations Density 0.006%

    No Known Activations