© 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. 34-GEMMASCOPE-RES-131K
    7. 107007
    Prev
    Next
    INDEX
    Explanations

    protocol, defineProperty, transistor

    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
     Alain
    -0.66
    imoto
    -0.66
    Bety
    -0.64
    dirkan
    -0.63
    beek
    -0.63
    越來越
    -0.63
     Vuelta
    -0.62
    goTo
    -0.61
    wang
    -0.61
     неу
    -0.60
    POSITIVE LOGITS
     які
    0.78
    crest
    0.73
     dzies
    0.72
    nata
    0.71
    documentElement
    0.70
    Or
    0.69
    mathematics
    0.69
     crest
    0.68
    idor
    0.68
    
    0.68
    Activations Density 0.382%

    No Known Activations