© 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. 47695
    Prev
    Next
    INDEX
    Explanations

    code, symbols, and punctuation

    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
    #(
    -1.03
    #$
    -0.90
    Both
    -0.80
     #(
    -0.77
    culares
    -0.75
    ###
    -0.75
     undefeated
    -0.75
    jetas
    -0.75
     Macau
    -0.75
     profitability
    -0.74
    POSITIVE LOGITS
    eping
    0.88
     costruire
    0.87
    apor
    0.84
    試し
    0.82
    ound
    0.81
     vocales
    0.79
     karşı
    0.79
    テト
    0.79
     ur
    0.77
     età
    0.76
    Activations Density 0.002%

    No Known Activations