© 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. 34-GEMMASCOPE-RES-131K
    7. 98361
    Prev
    Next
    INDEX
    Explanations

    writing or updating methods

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

    This neuron activates on programming–style method names and keywords (i.e. function declarations or calls such as Save, OnGUI, render, encode, paint, void, override).

    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
     return
    -0.82
    रीदारी
    -0.80
     Avez
    -0.75
    tift
    -0.75
     들
    -0.74
    FromString
    -0.73
     returning
    -0.71
    ဍ
    -0.71
     noft
    -0.71
     ballad
    -0.71
    POSITIVE LOGITS
     writeTo
    1.22
    appendTo
    1.20
    WriteTo
    1.16
    writeTo
    1.13
    forEach
    1.10
     incomplète
    0.98
     onto
    0.95
     into
    0.93
    addTo
    0.88
     addTo
    0.85
    Activations Density 0.015%

    No Known Activations