© 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. 112788
    Prev
    Next
    INDEX
    Explanations

    of the

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

    The neuron is selectively activating on the exact token “Of” (capital O, lowercase f).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    capitalized “Of” segments embedded in camelCase/PascalCase identifiers (XOfY-style names) within source code.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "Of" when it appears in camelCase identifiers or method names in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
    the
    -2.56
    ꯹
    -2.55
    which
    -2.31
    ႐
    -2.22
     and
    -2.17
     voordeel
    -2.13
    驀
    -2.11
    ſſen
    -2.09
    🤘
    -2.09
    诸多
    -2.08
    POSITIVE LOGITS
    Of
    3.83
    ’
    3.75
    𖣔
    3.02
    “
    2.91
    坶
    2.80
    偏偏
    2.77
    _
    2.72
    ꜆
    2.69
     Of
    2.59
    s
    2.52
    Activations Density 0.009%

    No Known Activations