© 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. 34-GEMMASCOPE-RES-131K
    7. 26031
    Prev
    Next
    INDEX
    Explanations

    version numbers and programming terms

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

    The neuron is chiefly activated by numeric tokens (especially version numbers and other digit or dot-delimited number sequences).

    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
    ლი
    -0.87
    umer
    -0.79
    AFS
    -0.76
     trastornos
    -0.76
    𝘩
    -0.73
    swatch
    -0.73
    Ejercicio
    -0.72
     subsystem
    -0.71
     acaso
    -0.71
     dommage
    -0.71
    POSITIVE LOGITS
     derive
    0.93
     nightly
    0.93
     derives
    0.82
    哲学
    0.81
    КТ
    0.81
    macro
    0.77
     Send
    0.76
     implementation
    0.75
     night
    0.75
     nighttime
    0.75
    Activations Density 0.023%

    No Known Activations