© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32232
    Prev
    Next
    INDEX
    Explanations

    names starting with buk or buck

    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_34/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
    Lack
    -0.84
    Dick
    -0.78
    ciu
    -0.77
    datastore
    -0.75
     Dick
    -0.75
     bushes
    -0.73
    まれて
    -0.71
    Wid
    -0.68
     {.
    -0.68
     Цер
    -0.67
    POSITIVE LOGITS
    jetunion
    0.83
    $-\
    0.79
    ጎ
    0.77
    ünsche
    0.77
     Aptitude
    0.75
     Commissione
    0.74
    ütfen
    0.73
     Alonzo
    0.72
    Mutant
    0.72
     rodzaj
    0.71
    Activations Density 0.012%

    No Known Activations