© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7845
    Prev
    Next
    INDEX
    Explanations

    input/output streams

    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
     know
    -1.88
     then
    -1.73
     selben
    -1.72
    ungalows
    -1.64
    有一个
    -1.59
     用
    -1.59
    嗒
    -1.55
     为
    -1.54
     seasoned
    -1.53
    phère
    -1.52
    POSITIVE LOGITS
    </i>
    2.47
    '
    1.94
    </h5>
    1.65
    Vendo
    1.62
    \
    1.55
    咫
    1.54
    "
    1.52
     oth
    1.52
     first
    1.50
    _
    1.47
    Activations Density 0.003%

    No Known Activations