© 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. 72090
    Prev
    Next
    INDEX
    Explanations

    versions and editions

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

    The neuron activates on digit‐containing tokens (numbers, years, and numeric identifiers).

    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
     навіть
    -1.10
    enlace
    -1.02
    エピ
    -1.02
    おわりに
    -1.02
     leurs
    -1.01
    キラキラ
    -1.00
    的心情
    -1.00
     llevará
    -0.99
    PARTE
    -0.99
     apoya
    -0.98
    POSITIVE LOGITS
     version
    1.80
     versions
    1.66
     of
    1.48
     everything
    1.28
     from
    1.22
     ones
    1.21
    版
    1.20
     anything
    1.17
     edition
    1.11
    版本
    1.09
    Activations Density 0.109%

    No Known Activations