© 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. 81325
    Prev
    Next
    INDEX
    Explanations

    data structures and attributes

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

    The neuron fires on the string “data” (in any context or as part of a larger token).

    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
    Tyl
    -0.73
     Distribute
    -0.69
     distribute
    -0.68
     prefeito
    -0.68
     Tyl
    -0.67
    african
    -0.67
    Tach
    -0.67
     Faithful
    -0.65
    adova
    -0.64
    ความ
    -0.63
    POSITIVE LOGITS
    structures
    1.05
    data
    0.98
     driven
    0.98
    driven
    0.91
    データ
    0.87
    Driven
    0.86
    Tables
    0.84
     Driven
    0.83
    uri
    0.82
    tică
    0.82
    Activations Density 0.053%

    No Known Activations