© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77438
    Prev
    Next
    INDEX
    Explanations

    officers of irrigation department

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

    The neuron activates on numeric tokens (e.g. multi‐digit numbers, years, amounts).

    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
     aiming
    -0.77
     supports
    -0.76
    icen
    -0.75
     troppo
    -0.74
    hithe
    -0.74
    POSAL
    -0.73
     easier
    -0.71
    disciplinar
    -0.71
    ladimir
    -0.71
     publicly
    -0.70
    POSITIVE LOGITS
     Enforcement
    1.04
     agency
    0.93
     ED
    0.92
    EDY
    0.87
    Enforcement
    0.84
    pośred
    0.80
     remand
    0.79
     アンティーク
    0.79
    rand
    0.77
    изображение
    0.77
    Activations Density 0.011%

    No Known Activations