© 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. 10-GEMMASCOPE-RES-131K
    7. 43321
    Prev
    Next
    INDEX
    Explanations

    utils; init(Polly’s Passat

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

    This neuron fires on code import/package lines that reference utility or common modules (e.g. “util,” “common,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ificados
    -1.40
    🗣
    -1.34
    aried
    -1.32
    硖
    -1.30
    rosserie
    -1.29
     marge
    -1.29
     ἡ
    -1.29
    ℞
    -1.28
     declaración
    -1.27
    —,
    -1.27
    POSITIVE LOGITS
    5
    2.02
    8
    1.96
    4
    1.67
    .
    1.66
    2
    1.62
    0
    1.61
    1
    1.59
    7
    1.58
     will
    1.56
    3
    1.50
    Activations Density 0.029%

    No Known Activations