© 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. 109460
    Prev
    Next
    INDEX
    Explanations

    code syntax and programming terms

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

    The neuron fires on numeric tokens (digits or numbers) appearing in code or text (e.g. years, IDs, CSS values).

    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
     Status
    -0.85
    STATUS
    -0.81
     STATUS
    -0.77
    ypos
    -0.74
    Status
    -0.74
     状态
    -0.72
    ależy
    -0.72
    เอก
    -0.71
    lith
    -0.70
    gast
    -0.69
    POSITIVE LOGITS
    tructor
    0.70
     dreamstime
    0.69
     interiores
    0.69
    taa
    0.68
     Inhibit
    0.66
     legends
    0.66
     equatorial
    0.65
     Zanzibar
    0.64
    nement
    0.64
    callback
    0.64
    Activations Density 0.047%

    No Known Activations