© 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. 115618
    Prev
    Next
    INDEX
    Explanations

    proper nouns and code comments

    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
     haar
    -0.77
    bois
    -0.76
    ᱪ
    -0.75
    GLOBALS
    -0.73
     RAM
    -0.73
    Optim
    -0.73
    тику
    -0.72
    请问
    -0.72
     dimension
    -0.71
    šov
    -0.71
    POSITIVE LOGITS
     Stär
    0.89
    feer
    0.83
     sincere
    0.82
     StringUtils
    0.81
    incere
    0.80
     tambahan
    0.76
    老头
    0.75
    ніе
    0.75
     uncon
    0.74
    IEL
    0.72
    Activations Density 0.007%

    No Known Activations