© 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. 38883
    Prev
    Next
    INDEX
    Explanations

    programming constructs and identifiers

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

    The neuron activates on programming API identifiers and class or method names—i.e. CamelCase or otherwise capitalized code symbols.

    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
     This
    -2.47
     With
    -2.38
     That
    -2.34
     urusan
    -2.28
    珽
    -2.22
     When
    -2.16
    鏐
    -2.03
     Ironically
    -2.02
     generasi
    -2.02
     Other
    -2.02
    POSITIVE LOGITS
    ”
    2.89
    ri
    2.83
    “
    2.66
     is
    2.52
    {
    2.44
    at
    2.39
    _
    2.31
    ha
    2.28
    </strong>
    2.27
    ’,
    2.27
    Activations Density 0.001%

    No Known Activations