© 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. 107303
    Prev
    Next
    INDEX
    Explanations

    code includes boolean

    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
     implementa
    -0.73
     Sunak
    -0.69
    Ỳ
    -0.68
    atv
    -0.66
    fällen
    -0.66
    分から
    -0.65
     impac
    -0.65
    reonine
    -0.63
     clazz
    -0.63
    PRINT
    -0.63
    POSITIVE LOGITS
     escenarios
    0.70
     картинки
    0.70
    ʡ
    0.68
    solete
    0.66
    ♓
    0.66
     regole
    0.66
     Infant
    0.65
     ranges
    0.65
     Pemberton
    0.64
    دل
    0.64
    Activations Density 0.062%

    No Known Activations