© 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. 42253
    Prev
    Next
    INDEX
    Explanations

    table row identifier

    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
    </strong>
    -3.30
    ↵
    -3.13
    </sub>
    -2.97
    ſu
    -2.80
    呖
    -2.73
    螓
    -2.73
    趿
    -2.73
     Houſe
    -2.72
     ſta
    -2.66
    gambarkan
    -2.50
    POSITIVE LOGITS
    ");
    3.17
    (
    3.14
     "
    2.88
    \
    2.86
    ?"
    2.81
    ."
    2.77
    ".
    2.73
    *
    2.73
    ">
    2.70
    ",
    2.67
    Activations Density 0.010%

    No Known Activations