© 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. 38997
    Prev
    Next
    INDEX
    Explanations

    code structure elements

    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
    3
    -1.39
     även
    -1.38
     also
    -1.33
    adalupe
    -1.28
     vulga
    -1.24
     samtidigt
    -1.21
    Lokal
    -1.20
     last
    -1.20
    archiwizowane
    -1.18
     doucement
    -1.18
    POSITIVE LOGITS
     when
    1.71
    when
    1.68
     if
    1.51
     that
    1.47
     what
    1.46
    𝗖
    1.46
     there
    1.36
    гает
    1.34
     who
    1.33
    there
    1.30
    Activations Density 0.130%

    No Known Activations