© 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. 39219
    Prev
    Next
    INDEX
    Explanations

    digits and numbers

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

    The neuron strongly activates on standalone numeric tokens (e.g. years, reference numbers, or other pure-digit items).

    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
     in
    -1.49
    鸰
    -1.35
     PUSTAKA
    -1.29
    Хотя
    -1.25
    itaji
    -1.23
    特長
    -1.22
    after
    -1.22
    ﾛ
    -1.20
    Generally
    -1.18
    Because
    -1.17
    POSITIVE LOGITS
    8
    1.61
    0
    1.56
    3
    1.52
    2
    1.48
    9
    1.45
    geddon
    1.45
    に入れる
    1.37
    に入れ
    1.37
    6
    1.36
    7
    1.34
    Activations Density 0.019%

    No Known Activations