© 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. 34-GEMMASCOPE-RES-131K
    7. 76680
    Prev
    Next
    INDEX
    Explanations

    go fmt package

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

    This neuron fires on occurrences of the Go “fmt” identifier (i.e. references to the fmt package).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    返し
    -1.02
    obacter
    -0.94
    ()[
    -0.93
    étricas
    -0.93
    drá
    -0.89
    泞
    -0.84
    izo
    -0.81
    lampa
    -0.79
     Übersetzung
    -0.79
    rounder
    -0.79
    POSITIVE LOGITS
     melat
    1.02
     otak
    0.96
     ì
    0.91
     giallo
    0.91
     WEEKLY
    0.90
     VISTA
    0.89
     墊
    0.89
     HIGHER
    0.88
     INITIAL
    0.88
     democra
    0.88
    Activations Density 0.003%

    No Known Activations