© 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. 84434
    Prev
    Next
    INDEX
    Explanations

    programming, legal, or scientific contexts

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

    The neuron is keyed to programming‐style identifiers and other uppercase technical tokens—e.g. library or module names, class/namespace names, version numbers, and similar code‐specific terms.

    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
    Uns
    -0.72
    Integer
    -0.70
     料
    -0.69
    biť
    -0.66
     premiers
    -0.66
    action
    -0.66
    atelier
    -0.66
    وقال
    -0.65
    elakaan
    -0.65
    Health
    -0.64
    POSITIVE LOGITS
     Snap
    0.73
     سن
    0.69
     snap
    0.69
    Tunes
    0.68
    Fountain
    0.67
    pread
    0.66
     gönder
    0.65
     fined
    0.65
    తి
    0.65
     queda
    0.65
    Activations Density 0.079%

    No Known Activations