© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 26015
    Prev
    Next
    INDEX
    Explanations

    Secretary General

    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
     OECD
    -0.79
     منطقه
    -0.79
    formas
    -0.75
     secretion
    -0.75
    fusion
    -0.73
    malar
    -0.69
    奖
    -0.68
     Interpol
    -0.67
    JF
    -0.67
     Claudius
    -0.67
    POSITIVE LOGITS
     USG
    0.84
    DEPARTMENT
    0.84
     UND
    0.81
     fiebre
    0.80
    蜱
    0.75
    izienz
    0.74
    Sustainable
    0.71
     Sustainable
    0.71
    時に
    0.71
     GA
    0.71
    Activations Density 0.017%

    No Known Activations