© 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. 82511
    Prev
    Next
    INDEX
    Explanations

    numbers and separators

    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
    formatics
    -1.00
    corns
    -0.90
    amir
    -0.88
    MemoryStream
    -0.86
    omorphisms
    -0.85
    atellite
    -0.85
    cepted
    -0.84
    >+</
    -0.84
    riad
    -0.84
    viti
    -0.84
    POSITIVE LOGITS
     untold
    0.82
    反対
    0.78
     penance
    0.76
     where
    0.75
    一方で
    0.74
    時代の
    0.71
    ﾋ
    0.69
     immediately
    0.69
     time
    0.67
     how
    0.67
    Activations Density 0.074%

    No Known Activations