© 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. 83244
    Prev
    Next
    INDEX
    Explanations

    filed court documents

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

    The neuron is triggered by code‐style and technical tokens—things like programming syntax, numbers, symbols, and other jargon rather than ordinary prose.

    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
     ten
    -0.88
    Ten
    -0.84
     Ten
    -0.83
    кре
    -0.74
     не
    -0.73
     Confederate
    -0.70
    ten
    -0.69
     Don
    -0.69
     convertible
    -0.68
     tổng
    -0.68
    POSITIVE LOGITS
     Rhys
    0.73
    🎹
    0.72
    ifdef
    0.71
     Rizal
    0.70
    ilane
    0.70
    querySelector
    0.68
    rechts
    0.68
    lookup
    0.67
     DWORD
    0.67
    Ronald
    0.66
    Activations Density 0.535%

    No Known Activations