© 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. 22-GEMMASCOPE-RES-131K
    7. 67816
    Prev
    Next
    INDEX
    Explanations

    combined effects, This week, Bellini

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

    This neuron fires on standalone underscore tokens (the “_” blank‐identifier or placeholder) in code.

    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
     に関する
    -1.20
     gekomen
    -1.20
    ються
    -1.17
    いかがでしたか
    -1.15
     elástico
    -1.13
     bordado
    -1.13
     estampado
    -1.12
    メガネ
    -1.12
     cordón
    -1.11
    に似
    -1.11
    POSITIVE LOGITS
    g
    1.20
    U
    1.15
    Ingredienti
    0.97
    R
    0.96
     debuts
    0.96
    a
    0.95
    o
    0.94
    y
    0.93
    1
    0.93
    aa
    0.93
    Activations Density 0.002%

    No Known Activations