© 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. 38941
    Prev
    Next
    INDEX
    Explanations

    Rohit Roy Sachin Sheeran

    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
     meditative
    -2.89
     que
    -2.89
     That
    -2.80
     exuberant
    -2.80
     for
    -2.70
     treacherous
    -2.66
     oppressive
    -2.58
     metaphorical
    -2.58
     unrelenting
    -2.55
    !!!!!
    -2.50
    POSITIVE LOGITS
    四处
    2.95
    靦
    2.89
    縠
    2.73
     laboratorium
    2.56
     beig
    2.50
     BEING
    2.48
    糶
    2.47
     amd
    2.45
     présenter
    2.45
    撿
    2.42
    Activations Density 0.002%

    No Known Activations