© 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. 54301
    Prev
    Next
    INDEX
    Explanations

    adipose tissue components

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

    This neuron activates for terms related to adipose tissue and adipocyte biology, particularly recognizing words like "adiponectin," "adipokine," and "adiposity."

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

    The neuron detects occurrences of the “adipo-” prefix (e.g. in adiponectin, adipogenesis, adipo kine, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     demand
    -0.74
    auf
    -0.72
     marginal
    -0.71
    ambar
    -0.71
    demand
    -0.70
    andeep
    -0.70
    ="#
    -0.70
     sympathetic
    -0.70
    cwd
    -0.68
    ">!
    -0.68
    POSITIVE LOGITS
     Ceramics
    0.83
     Crimin
    0.81
     aime
    0.78
    bca
    0.76
     сцен
    0.75
    顺序
    0.74
     Confirmation
    0.74
    ঊ
    0.73
    दै
    0.73
    坂
    0.73
    Activations Density 0.038%

    No Known Activations