© 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. 16063
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and names

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

    The neuron fires primarily on numerical tokens (digits or multi‐digit numbers) in the text.

    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
    şağı
    -0.96
    щенко
    -0.92
     jupe
    -0.89
     APPELL
    -0.86
    hradun
    -0.86
    寸
    -0.86
     Noruega
    -0.85
     partag
    -0.85
    aların
    -0.85
    quiera
    -0.83
    POSITIVE LOGITS
     our
    0.95
     encontramos
    0.92
     caminho
    0.91
     about
    0.90
     include
    0.86
     incluye
    0.85
     เรา
    0.84
     ourselves
    0.82
     ベン
    0.81
    тная
    0.81
    Activations Density 0.002%

    No Known Activations