© 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. 22-GEMMASCOPE-RES-131K
    7. 27750
    Prev
    Next
    INDEX
    Explanations

    purpose or toward

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

    The neuron activates on numeric tokens (integers or decimals) 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
    が
    -2.02
     as
    -1.88
     for
    -1.78
    や
    -1.77
    を
    -1.74
    と
    -1.70
     because
    -1.63
     mainly
    -1.62
    そして
    -1.59
    などを
    -1.59
    POSITIVE LOGITS
    ところに
    2.05
    為に
    2.02
    corrhi
    1.97
    様な
    1.95
    久し
    1.95
    の方に
    1.84
    すっ
    1.77
    ほうがいい
    1.73
    感じが
    1.68
    場所で
    1.66
    Activations Density 0.120%

    No Known Activations