© 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. 87093
    Prev
    Next
    INDEX
    Explanations

    section labels and markup

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

    The neuron fires on structural metadata and markup tokens—things like license‐header punctuation, section identifiers (e.g. “sect”), slash separators, and other file‐header or comment markers.

    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
    getManager
    -0.78
    logError
    -0.77
    bookings
    -0.77
     terrible
    -0.74
    ᶦ
    -0.73
    dbo
    -0.71
    Elemental
    -0.69
     strong
    -0.69
    幟
    -0.69
     unten
    -0.68
    POSITIVE LOGITS
     Tổng
    0.75
     Proposal
    0.73
    нительно
    0.71
    EXTER
    0.71
     défaite
    0.71
    licy
    0.70
     proposal
    0.70
     przer
    0.70
     ドライ
    0.70
     proposals
    0.70
    Activations Density 0.002%

    No Known Activations