© 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. 10-GEMMASCOPE-RES-131K
    4. 118847
    Prev
    Next
    INDEX
    Explanations

    immune response and levels

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

    The neuron detects the phrase "immune response" 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
    indeer
    -1.50
    ⻓
    -1.48
     terakhir
    -1.48
    ⇡
    -1.45
    adır
    -1.43
    ixar
    -1.42
    mpions
    -1.36
    图源
    -1.34
     hoàng
    -1.34
     "}";
    -1.34
    POSITIVE LOGITS
    -
    1.67
     into
    1.45
     during
    1.44
    H
    1.36
     mexicana
    1.36
     would
    1.27
     still
    1.26
    R
    1.20
    E
    1.20
     like
    1.19
    Activations Density 0.097%

    No Known Activations