© 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. 22-GEMMASCOPE-RES-131K
    7. 28261
    Prev
    Next
    INDEX
    Explanations

    code formatting

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

    This neuron detects numeric literals (sequences of 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
     only
    -2.00
    が
    -1.98
     mostly
    -1.69
    を
    -1.69
     perhaps
    -1.66
     probably
    -1.63
     still
    -1.57
     mainly
    -1.56
     just
    -1.54
     possibly
    -1.51
    POSITIVE LOGITS
    久し
    1.82
    えっ
    1.74
    あぁ
    1.70
    あー
    1.70
    の方に
    1.65
    すっ
    1.63
    為に
    1.63
    さぁ
    1.60
    急に
    1.59
    場所で
    1.58
    Activations Density 0.034%

    No Known Activations