© 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. 39187
    Prev
    Next
    INDEX
    Explanations

    programming util

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

    The neuron fires on occurrences of the standalone identifier “util” (e.g. in import or require statements).

    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
    origami
    -1.47
    Cdb
    -1.47
    akk
    -1.45
     ícone
    -1.45
     utveckling
    -1.43
     hiçbir
    -1.41
     wichtiger
    -1.40
    𝘕
    -1.34
    镠
    -1.33
    ecutable
    -1.31
    POSITIVE LOGITS
    4
    2.03
    To
    2.03
    7
    1.97
    6
    1.88
    For
    1.78
    1
    1.77
    F
    1.75
    The
    1.72
    2
    1.70
    3
    1.67
    Activations Density 0.001%

    No Known Activations