© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 21364
    Prev
    Next
    INDEX
    Explanations

    carbo hydrate

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

    The neuron detects the word "carbohydrate" and its variants in scientific and nutritional contexts.

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

    The neuron activates on occurrences of the substring “carbo” (as in “carbohydrate,” “carbo-,” etc.) in scientific or biochemical contexts.

    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
     andere
    -2.73
    '
    -2.66
     beker
    -2.34
    鈇
    -2.25
     OTHER
    -2.19
     dando
    -2.17
     autres
    -2.17
     the
    -2.11
    './
    -2.11
    .」
    -2.09
    POSITIVE LOGITS
    there
    3.42
    This
    2.69
    Despite
    2.64
    of
    2.63
    T
    2.59
    when
    2.56
     層
    2.55
    Since
    2.55
    which
    2.52
     當
    2.50
    Activations Density 0.001%

    No Known Activations