© 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. 7611
    Prev
    Next
    INDEX
    Explanations

    code punctuation

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

    This neuron responds to programming-language function or method call tokens (identifiers followed by parentheses).

    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
    ätigung
    -1.75
     cuyos
    -1.58
     akik
    -1.57
     RelativeLayout
    -1.55
    medriver
    -1.51
     UIColor
    -1.51
    
    -1.49
     endforeach
    -1.48
     cuyas
    -1.47
    ⧠
    -1.45
    POSITIVE LOGITS
    e
    1.76
    唸
    1.44
    是
    1.34
    n
    1.33
     pandora
    1.33
    h
    1.33
    b
    1.32
    d
    1.32
    z
    1.32
    x
    1.31
    Activations Density 0.009%

    No Known Activations