© 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. 14617
    Prev
    Next
    INDEX
    Explanations

    DateTime and AsyncTask

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

    This neuron detects single tokens in PascalCase or CamelCase (i.e. words with internal uppercase letters, like “DateTime,” “AsyncTask,” or “DateTimePicker”).

    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
    </strong>
    -3.20
    </h3>
    -2.67
    the
    -2.66
    0
    -2.58
    旆
    -2.50
    ating
    -2.45
    淠
    -2.44
    𞤢
    -2.36
    蘩
    -2.20
    脔
    -2.20
    POSITIVE LOGITS
    as
    2.72
    s
    2.67
    ی
    2.39
    鹉
    2.36
    .}(
    2.28
    渽
    2.19
    та
    2.19
    aabb
    2.13
     To
    2.11
    唎
    2.08
    Activations Density 0.006%

    No Known Activations