© 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. 11055
    Prev
    Next
    INDEX
    Explanations

    performances or broadcasts

    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
     \
    -2.61
    的东西
    -2.19
    “
    -2.16
    薮
    -2.08
     but
    -2.02
     tries
    -1.94
    each
    -1.93
    ان
    -1.91
     \&
    -1.83
    専用
    -1.82
    POSITIVE LOGITS
     ewig
    2.38
    derdag
    2.20
     disseminating
    2.11
    "}}>
    2.11
    ☆☆☆☆
    2.09
     merkwür
    2.05
     gesprochen
    2.02
    釙
    2.00
    entikan
    2.00
     gefährlich
    1.98
    Activations Density 0.019%

    No Known Activations