© 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. 540
    Prev
    Next
    INDEX
    Explanations

    Leah Buckareff, Leandro Erlich, Leah O'Rourke

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

    The neuron fires strongly on the discrete symbols, numbers, and uppercase‐style tokens that occur in formal citations (e.g. “v.”, numerical volumes and years, all‐caps macros or acronyms).

    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
     fim
    -0.77
    жно
    -0.74
     directement
    -0.73
     gemacht
    -0.73
    డ్
    -0.71
     bookmark
    -0.71
    mam
    -0.68
     Ρ
    -0.68
     tra
    -0.67
    setopt
    -0.67
    POSITIVE LOGITS
     söyl
    0.82
    стта
    0.82
     petitioners
    0.81
    contributor
    0.80
     ileg
    0.80
    ⱱ
    0.79
    という言葉
    0.78
    ضى
    0.78
    sition
    0.75
    setRotation
    0.74
    Activations Density 0.153%

    No Known Activations