© 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. 99309
    Prev
    Next
    INDEX
    Explanations

    d-amino, dDAVP, dCIN, d3Service

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

    instances of the letter 'd' appearing in code or technical contexts, especially when representing parameters or variables.

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

    The neuron is triggered by standalone lowercase “d” tokens (e.g. the single-letter “d” that appears in code attributes or citation markers).

    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
    e
    -3.22
    </strong>
    -3.16
    </h3>
    -2.88
    al
    -2.86
    in
    -2.77
    鋱
    -2.73
    re
    -2.50
    h
    -2.48
    ènement
    -2.41
    </sub>
    -2.39
    POSITIVE LOGITS
    '
    3.98
    \
    3.56
    *
    3.36
    $
    2.84
    If
    2.80
    /
    2.80
    ING
    2.48
     But
    2.48
    dersfield
    2.42
     '
    2.34
    Activations Density 0.046%

    No Known Activations