© 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. 129300
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens—particularly standalone numbers or figures (e.g. prices, dates, statistics).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    numbers and decimals

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    獃
    -1.58
    鷽
    -1.55
     plafon
    -1.52
    饜
    -1.47
    !=-
    -1.45
     rire
    -1.45
    𓋼
    -1.43
     maniere
    -1.42
    หรือ
    -1.41
    鮡
    -1.41
    POSITIVE LOGITS
     "
    1.93
    ,
    1.77
    n
    1.76
    G
    1.75
    R
    1.73
     for
    1.73
    O
    1.73
    f
    1.71
    E
    1.65
    H
    1.63
    Activations Density 0.030%

    No Known Activations