© 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. 72525
    Prev
    Next
    INDEX
    Explanations

    numbers and identifiers

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

    The neuron is specialized for spotting numeric tokens (especially multidigit and decimal 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
    Concluding
    -0.86
     médica
    -0.80
    стит
    -0.79
    hem
    -0.78
     leadership
    -0.75
    ">−
    -0.75
    şağı
    -0.74
    **/
    -0.73
    σκευ
    -0.73
     NSError
    -0.73
    POSITIVE LOGITS
     angekommen
    0.76
     decre
    0.75
     potrivit
    0.74
     CHP
    0.71
    npr
    0.71
     africains
    0.71
     Sephora
    0.70
     entrée
    0.70
    Grin
    0.70
    KOS
    0.69
    Activations Density 0.290%

    No Known Activations