© 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. 71910
    Prev
    Next
    INDEX
    Explanations

    events and dates

    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
     continually
    -1.54
    ͊
    -1.49
    ౭
    -1.45
     وت
    -1.45
     développer
    -1.39
     prendre
    -1.38
     و
    -1.38
     astonishing
    -1.38
     tremendous
    -1.37
     amazingly
    -1.37
    POSITIVE LOGITS
     at
    1.80
     on
    1.69
     because
    1.64
     while
    1.53
     thirteen
    1.41
     this
    1.41
     in
    1.40
     despite
    1.39
     by
    1.35
     or
    1.31
    Activations Density 0.167%

    No Known Activations