© 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. 22291
    Prev
    Next
    INDEX
    Explanations

    of the form

    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
    ovna
    -1.83
     vixion
    -1.82
     墊
    -1.80
     現貨
    -1.80
    naments
    -1.79
    leine
    -1.77
    ープン
    -1.73
    
    -1.72
    😵
    -1.67
    actéristi
    -1.66
    POSITIVE LOGITS
     like
    1.90
     /
    1.84
     include
    1.82
     :
    1.76
     that
    1.76
    .”
    1.70
     at
    1.68
     of
    1.66
     a
    1.53
     hervorragend
    1.53
    Activations Density 0.033%

    No Known Activations