© 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. 116544
    Prev
    Next
    INDEX
    Explanations

    asphalt modified bitumen cement

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

    This neuron specializes in detecting technical material or substance terms (e.g., cement, asphalt, emulsions, pitch) in the text.

    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
    teca
    -0.82
    oley
    -0.77
    eryllium
    -0.77
    ër
    -0.76
     ẩn
    -0.76
    ハンドメイド
    -0.74
    RemoveAt
    -0.74
     zeroes
    -0.73
    DataPropertyName
    -0.73
     analyzed
    -0.71
    POSITIVE LOGITS
     bitumen
    0.95
    Bind
    0.86
     refinery
    0.85
    binder
    0.84
    modif
    0.83
     binder
    0.83
    Ɠ
    0.82
     太
    0.81
    Grade
    0.81
     PG
    0.79
    Activations Density 0.009%

    No Known Activations