© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66631
    Prev
    Next
    INDEX
    Explanations

    code annotations and functions

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

    This neuron detects programming‐related identifiers and metadata (e.g. code declarations, annotations, and attribute names) in the text.

    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
    i
    -1.09
     stesso
    -1.09
    另
    -1.07
    楽しい
    -1.05
     different
    -1.05
    T
    -1.04
    ization
    -1.03
    a
    -1.02
    your
    -1.00
    你的
    -1.00
    POSITIVE LOGITS
    planung
    1.28
     vorigen
    1.20
     директор
    1.20
     Diputados
    1.20
     متحده
    1.20
    wirkt
    1.20
    ’?
    1.18
    徨
    1.16
    Ὁ
    1.16
    calaureate
    1.15
    Activations Density 0.000%

    No Known Activations