© 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. 10-GEMMASCOPE-RES-131K
    7. 19795
    Prev
    Next
    INDEX
    Explanations

    weakness or impairment

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

    The neuron activates for the word "lame" and similar words like "limp" that refer to physical weakness or disability.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    たまた
    -1.89
    In
    -1.88
     próprias
    -1.67
    Zeneca
    -1.63
     Are
    -1.63
     worries
    -1.59
     versões
    -1.55
     fontes
    -1.52
     of
    -1.48
    Thing
    -1.48
    POSITIVE LOGITS
    ców
    1.93
    ׅ
    1.73
    isiert
    1.73
    Kemudian
    1.70
    ",
    1.69
    汌
    1.67
    ’
    1.64
    Siapa
    1.61
    ),
    1.60
    渴
    1.56
    Activations Density 0.006%

    No Known Activations