© 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. 101653
    Prev
    Next
    INDEX
    Explanations

    Saint names and places

    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
    '
    -1.76
    -
    -1.64
    [
    -1.58
    </strong>
    -1.57
     hjemmes
    -1.53
     netts
    -1.52
     freaking
    -1.48
     ombro
    -1.38
     someone
    -1.38
    obacz
    -1.38
    POSITIVE LOGITS
    "]();
    1.61
    FormUrlEncoded
    1.48
    (!__
    1.46
     uneasy
    1.42
     \\
    1.41
     даже
    1.38
    }}">
    1.38
     on
    1.37
    </td>
    1.34
    makeConstraints
    1.34
    Activations Density 0.025%

    No Known Activations