© 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. 34-GEMMASCOPE-RES-131K
    7. 57344
    Prev
    Next
    INDEX
    Explanations

    Wood

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

    The neuron activates on tokens containing the substring “wood” (e.g. Wood’s, Woodside, Wood Street).

    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
    denominator
    -0.81
    立场
    -0.81
    <0xC8>
    -0.80
    懐かしい
    -0.80
    ceaux
    -0.80
     vestig
    -0.77
     אתם
    -0.77
    われます
    -0.77
    ENDAR
    -0.75
     Και
    -0.75
    POSITIVE LOGITS
    wod
    0.83
    americanos
    0.81
    nog
    0.75
    Wood
    0.74
     Wood
    0.72
     当
    0.72
    Ω
    0.71
     ещё
    0.71
     еще
    0.69
    ⬎
    0.69
    Activations Density 0.026%

    No Known Activations