© 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. 41745
    Prev
    Next
    INDEX
    Explanations

    biological and immune response

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

    The neuron detects the word "response" particularly in scientific and medical contexts.

    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
    -1.95
    虯
    -1.95
    蜴
    -1.94
     этом
    -1.93
    </i>
    -1.92
    举动
    -1.92
    物资
    -1.88
     успеха
    -1.88
    哎呀
    -1.84
    Efter
    -1.83
    POSITIVE LOGITS
     of
    2.52
    “
    2.20
     in
    2.09
    髎
    2.06
    .”
    2.02
    вого
    2.02
    onOptions
    2.00
    佧
    1.99
    銕
    1.98
    Ligações
    1.96
    Activations Density 0.027%

    No Known Activations