© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 76456
    Prev
    Next
    INDEX
    Explanations

    code comments and structure

    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
    twenty
    -0.73
     twenty
    -0.71
     forty
    -0.69
    ो
    -0.69
     Jenny
    -0.69
     overtly
    -0.69
    Jenny
    -0.69
     Forty
    -0.68
    forty
    -0.68
    ओ
    -0.67
    POSITIVE LOGITS
     ۱۱
    0.75
    EXPRESSION
    0.72
     ۱۲
    0.72
     nace
    0.69
    STREET
    0.68
     costos
    0.67
    erii
    0.66
    啲
    0.66
     Wrath
    0.66
    ЭС
    0.65
    Activations Density 0.192%

    No Known Activations