© 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. 22-GEMMASCOPE-RES-131K
    7. 15776
    Prev
    Next
    INDEX
    Explanations

    keywords preceding common code constructs

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

    This neuron activates on backtick characters marking code spans or blocks.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     all
    -1.79
     any
    -1.74
     by
    -1.60
    賄
    -1.59
    幹線
    -1.59
     as
    -1.56
     even
    -1.56
    ！(
    -1.55
    餃
    -1.55
    Condol
    -1.48
    POSITIVE LOGITS
    を探す
    1.85
     beliebt
    1.71
     áng
    1.57
     aktualisiert
    1.55
    扨
    1.52
     nossas
    1.49
     teuer
    1.48
     angepasst
    1.48
    からお
    1.46
     geliefert
    1.45
    Activations Density 0.003%

    No Known Activations