© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 9400
    Prev
    Next
    INDEX
    Explanations

    Induction, Q, Ent

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

    The neuron activates on numeric tokens—i.e. sequences of digits (page numbers, IDs, multi‐digit numbers).

    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
    izie
    -1.01
    roland
    -0.98
     of
    -0.94
    ряду
    -0.93
     buoni
    -0.92
     lieto
    -0.92
     eene
    -0.91
     además
    -0.91
     segítség
    -0.90
     kış
    -0.90
    POSITIVE LOGITS
    もしか
    1.02
    着一个
    0.98
    収録曲
    0.93
    idxs
    0.93
    金
    0.92
     cardíaca
    0.91
    これも
    0.91
    ení
    0.90
    NSIndexPath
    0.88
    懸命
    0.88
    Activations Density 0.000%

    No Known Activations