© 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. 84476
    Prev
    Next
    INDEX
    Explanations

    questions starting with Q:

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

    This neuron fires on mentions of specific neural-network module names (e.g. “Lstm,” “Nonlinearity Component,” dropout, output, schedule) in code comments or documentation.

    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
     manchester
    -0.83
    PORTE
    -0.83
     Vande
    -0.74
     échanti
    -0.74
     Arre
    -0.72
     germany
    -0.71
    巴黎
    -0.70
     islamic
    -0.70
    sample
    -0.70
     นัก
    -0.69
    POSITIVE LOGITS
     recipes
    0.85
     ark
    0.82
    ark
    0.74
    tips
    0.72
     recipe
    0.71
     Kal
    0.71
    fst
    0.69
    Inters
    0.69
     ut
    0.69
    KAL
    0.68
    Activations Density 0.017%

    No Known Activations