© 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. 34-GEMMASCOPE-RES-131K
    7. 62864
    Prev
    Next
    INDEX
    Explanations

    CoffeeScript arrow functions

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

    The neuron is looking for CoffeeScript function-definition syntax, in particular the “→” (->) arrow token.

    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
    дир
    -0.80
     fürs
    -0.80
    fitri
    -0.79
    нівер
    -0.78
     maxlength
    -0.77
     bào
    -0.76
    ansas
    -0.74
    utel
    -0.73
     Савез
    -0.73
    क्षण
    -0.73
    POSITIVE LOGITS
     付け
    0.90
     Renaud
    0.90
     Attitude
    0.86
     continuare
    0.85
     lega
    0.85
     paradigma
    0.84
     Steen
    0.81
     materiale
    0.79
    zoni
    0.78
     ref
    0.77
    Activations Density 0.010%

    No Known Activations