© 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. 22304
    Prev
    Next
    INDEX
    Explanations

    botanical, engineers, house, frameworks

    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
    .
    -1.78
    :
    -1.56
     их
    -1.48
     /
    -1.47
    ,
    -1.38
    참고
    -1.36
     leur
    -1.30
     I
    -1.30
    𝟻
    -1.28
     of
    -1.27
    POSITIVE LOGITS
     zina
    1.59
     tenda
    1.59
     nors
    1.57
    戩
    1.56
     verba
    1.53
     墊
    1.52
     sula
    1.49
     fua
    1.48
     sende
    1.48
     metu
    1.46
    Activations Density 8.720%

    No Known Activations