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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8631
    Prev
    Next
    INDEX
    Explanations

    human concepts and nature

    np_acts-logits-general · gemini-2.5-flash-lite

    indented lines in a document or text with standard paragraph formatting structure.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron primarily fires on numeric tokens—dates, measurements, counts, and other numbers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     to
    -1.89
     then
    -1.70
     always
    -1.60
     Then
    -1.56
    就算
    -1.45
    h
    -1.45
     I
    -1.41
     Always
    -1.40
     even
    -1.40
    ll
    -1.40
    POSITIVE LOGITS
    väg
    1.62
    也會
    1.60
    pography
    1.52
     Milán
    1.52
    湉
    1.46
     Spanyol
    1.44
    ximately
    1.42
     maría
    1.41
    schwe
    1.41
     similares
    1.41
    Activations Density 0.121%

    No Known Activations