© 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. 49302
    Prev
    Next
    INDEX
    Explanations

    heavy rain and cold

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

    This neuron activates primarily on numeric tokens (multi-digit numbers) 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
    偶
    -0.90
    roughts
    -0.85
     Schatten
    -0.84
     movements
    -0.81
     days
    -0.81
     بع
    -0.80
     Meteorological
    -0.79
    itaire
    -0.79
     phenomenon
    -0.79
    фраструк
    -0.77
    POSITIVE LOGITS
     rain
    1.46
     blinding
    1.29
     sle
    1.18
     gale
    1.13
     pouring
    1.09
     icy
    1.09
     heavy
    1.02
    雨が
    1.01
     freezing
    0.98
     raging
    0.96
    Activations Density 0.032%

    No Known Activations