© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86196
    Prev
    Next
    INDEX
    Explanations

    accessing key value

    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
    -1.32
     even
    -1.32
    2
    -1.23
    *
    -1.23
     if
    -1.16
    年も
    -1.09
    یم
    -1.09
     даже
    -1.09
    》：
    -1.07
     estekak
    -1.06
    POSITIVE LOGITS
     nisso
    1.42
    ',
    1.41
    </th>
    1.38
    넵
    1.34
    thschild
    1.32
    拶
    1.32
    当たる
    1.31
     lastly
    1.30
    』『
    1.28
     desses
    1.27
    Activations Density 0.009%

    No Known Activations