© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130056
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on Ruby instance‐variable references (tokens beginning with “@”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    controller nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    衿
    -1.90
    และ
    -1.88
     Если
    -1.82
     It
    -1.70
    Географи
    -1.63
    蛧
    -1.62
     žena
    -1.62
     kompetisi
    -1.61
     kabát
    -1.61
     Incluye
    -1.61
    POSITIVE LOGITS
    B
    2.25
    D
    2.25
    ↵
    2.16
    H
    2.03
    E
    1.93
    >
    1.90
    O
    1.88
    '
    1.88
    R
    1.86
    M
    1.84
    Activations Density 0.005%

    No Known Activations