© 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. 112411
    Prev
    Next
    INDEX
    Explanations

    javascript code expressions

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

    the `.call(` method invocation pattern in JavaScript code

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

    This neuron detects identifier‐followed opening parentheses, i.e. spots where a function or method is being invoked.

    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
     vastly
    -1.76
    逦
    -1.63
     pérd
    -1.61
     ferocious
    -1.59
     ܪ
    -1.54
    􏰀
    -1.52
     deliciously
    -1.52
    が無い
    -1.48
    鲮
    -1.48
    
    -1.48
    POSITIVE LOGITS
    Like
    1.69
     нам
    1.63
     and
    1.57
    what
    1.54
     what
    1.53
     or
    1.48
     where
    1.43
    ....
    1.43
     sehr
    1.40
     just
    1.38
    Activations Density 0.004%

    No Known Activations