© 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. 66751
    Prev
    Next
    INDEX
    Explanations

    string definitions or titles

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

    The neuron strongly activates on numeric tokens and numeric sequences (e.g. standalone numbers, numbers with decimal points, or long digit strings).

    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
     pistolet
    -1.21
     stratég
    -1.16
     italie
    -1.01
    イタリア
    -1.00
     podes
    -1.00
     cuivre
    -0.99
     hoger
    -0.98
     vulgaires
    -0.98
     aquí
    -0.97
    コスト
    -0.97
    POSITIVE LOGITS
    Recep
    1.09
    </strong>
    1.09
    ar
    1.06
    Compati
    1.05
     too
    1.04
     provar
    1.00
    Soli
    0.99
     reda
    0.97
    謳
    0.96
     even
    0.95
    Activations Density 0.001%

    No Known Activations