© 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. 105219
    Prev
    Next
    INDEX
    Explanations

    javascript object prototype

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

    function calls that create or instantiate data structures (arrays, DataFrames, or objects).

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

    The neuron fires on mixed-case programming identifiers (e.g. camelCase or PascalCase function/method 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
     to
    -2.02
    鹛
    -1.55
     here
    -1.55
     "
    -1.52
     ultimately
    -1.50
     In
    -1.50
     will
    -1.49
     vítima
    -1.37
    }$$
    -1.34
     elige
    -1.34
    POSITIVE LOGITS
    Recently
    1.87
    Takk
    1.70
    Consequently
    1.68
    However
    1.65
    Already
    1.61
    Surprisingly
    1.60
    Interestingly
    1.59
    Previously
    1.56
    焄
    1.55
    Also
    1.53
    Activations Density 0.002%

    No Known Activations