© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42949
    Prev
    Next
    INDEX
    Explanations

    programming terms and library functions

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

    The neuron fires on programming identifiers or keywords written in CamelCase or with an initial capital letter (e.g. class, constructor, logger, function names).

    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
    ,”
    -2.91
    ’
    -2.80
    “,
    -2.64
    ‘
    -2.56
    m
    -2.45
    ’,
    -2.45
    焢
    -2.25
    ‘‘
    -2.16
    香り
    -2.13
    </u>
    -2.08
    POSITIVE LOGITS
     considerado
    2.30
     has
    2.30
    ▤
    2.25
    </h2>
    2.20
     indicates
    2.19
     "
    2.14
     experimentar
    2.13
    bollah
    2.08
     debía
    2.03
     costumbre
    2.03
    Activations Density 0.136%

    No Known Activations