© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 118952
    Prev
    Next
    INDEX
    Explanations

    By.considering, By.selector, By.key

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

    method calls and function invocations in programming code, particularly those with parentheses following identifiers like "By", "Selector", "Dense", "contains", "get", and "Box".

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on programming identifiers and API names (e.g. class or method names like “By”, “Selector”, “Dense”, “contains”).

    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
    !”
    -1.80
    ):
    -1.75
    )
    -1.71
    </em>
    -1.65
    -1.63
    ！　
    -1.60
    ’-
    -1.60
    -1.59
    ’,
    -1.57
     whom
    -1.52
    POSITIVE LOGITS
     of
    2.31
    s
    1.77
    焄
    1.72
     置物
    1.66
    '
    1.63
     również
    1.52
     juzgar
    1.52
     justement
    1.48
     koul
    1.44
     accordo
    1.44
    Activations Density 0.002%

    No Known Activations