© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 56798
    Prev
    Next
    INDEX
    Explanations

    Un categorized

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

    The neuron is primarily triggered by sequences of digits (especially phone‐number style numeric strings).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     meios
    -0.85
    cần
    -0.84
     يخ
    -0.78
    preneurship
    -0.77
    ：“……”
    -0.76
    幻
    -0.76
    ALS
    -0.75
    igram
    -0.74
     سيارة
    -0.74
     illustrate
    -0.73
    POSITIVE LOGITS
    8
    1.05
    ೮
    0.93
     ۸
    0.81
     TIEMPO
    0.76
    ائع
    0.76
    organizer
    0.75
    asgi
    0.75
     aguacate
    0.74
    Zurück
    0.73
    Mileage
    0.73
    Activations Density 0.011%

    No Known Activations