© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 33928
    Prev
    Next
    INDEX
    Explanations

    months, names, or locations

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

    The neuron activates on numeric tokens (numbers, dates, measurements, or digits) 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_22/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
     this
    -1.18
     that
    -1.03
    föl
    -1.01
    Alguns
    -1.00
    dö
    -0.99
    ouse
    -0.98
    icted
    -0.97
    ℅
    -0.95
     which
    -0.94
     these
    -0.94
    POSITIVE LOGITS
     lác
    1.13
     Bathrooms
    1.12
     khắp
    1.11
     nachher
    1.11
     рассказывает
    1.09
    诟
    1.08
    んでる
    1.08
     кажется
    1.05
     сейчас
    1.05
    んだり
    1.05
    Activations Density 0.071%

    No Known Activations