© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 92237
    Prev
    Next
    INDEX
    Explanations

    method declarations that throw

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

    The neuron fires on the parentheses of function or method declarations/calls, effectively detecting method signatures (i.e. names followed by “(…)”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     tapping
    -0.92
     repeatedly
    -0.92
     mash
    -0.88
     TAP
    -0.88
     hammering
    -0.85
    Repeated
    -0.81
    है
    -0.79
    Mash
    -0.79
    TAP
    -0.76
     %=
    -0.74
    POSITIVE LOGITS
     throws
    3.45
    throws
    2.77
     throw
    2.42
     thrown
    2.31
     threw
    2.25
     throwing
    2.05
    throw
    1.99
    throwing
    1.88
    Throws
    1.88
    thrown
    1.85
    Activations Density 0.024%

    No Known Activations