© 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. 21367
    Prev
    Next
    INDEX
    Explanations

    pulled out, get out, drag out

    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
     trotzdem
    -1.48
     putea
    -1.43
    _
    -1.40
    ◇
    -1.39
     Città
    -1.38
     solu
    -1.34
    現
    -1.31
    you
    -1.30
    we
    -1.29
     additions
    -1.28
    POSITIVE LOGITS
    éraire
    1.66
    すでに
    1.55
     Obtaining
    1.52
     Commonly
    1.51
     Oft
    1.50
    сезон
    1.48
     Adop
    1.47
    𓁹
    1.44
     Offering
    1.44
    痪
    1.41
    Activations Density 0.014%

    No Known Activations