© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99263
    Prev
    Next
    INDEX
    Explanations

    dough and related words

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

    The neuron strongly activates on occurrences of the word “dough” (and related baking actions).

    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
    7
    -3.27
    d
    -2.98
    ’
    -2.94
    or
    -2.91
    3
    -2.86
    e
    -2.83
    t
    -2.72
    S
    -2.66
    Z
    -2.64
    IN
    -2.63
    POSITIVE LOGITS
    <bos>
    3.13
    顰
    2.61
    錚
    2.47
     ก็
    2.39
     If
    2.30
    笫
    2.28
    𓆟
    2.27
    ዡ
    2.23
     they
    2.20
    {
    2.20
    Activations Density 0.005%

    No Known Activations