© 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. 99952
    Prev
    Next
    INDEX
    Explanations

    Promise methods and async operations

    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
     \"
    -1.66
     ‚
    -1.64
     \#
    -1.63
    ⼥
    -1.61
     milyen
    -1.58
    uminazione
    -1.51
     hanno
    -1.49
     »,
    -1.49
    家用
    -1.47
     (...)
    -1.46
    POSITIVE LOGITS
     that
    1.69
    媗
    1.58
    菒
    1.53
    ICOLON
    1.52
    </b>
    1.52
     хоче
    1.45
     keinerlei
    1.45
     розпові
    1.44
    ا
    1.42
    Other
    1.41
    Activations Density 0.016%

    No Known Activations