© 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. 25751
    Prev
    Next
    INDEX
    Explanations

    numbers and separators

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

    The neuron fires on numeric tokens or substrings containing digits.

    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
     tormented
    -1.11
    了不少
    -1.10
    了许多
    -1.09
    ஊ
    -1.09
    coloriage
    -1.07
     різних
    -1.07
    のかも
    -1.06
    Akan
    -1.06
     росій
    -1.05
     MAKES
    -1.04
    POSITIVE LOGITS
    ק
    1.16
    «
    1.15
     was
    1.15
     mxArray
    1.13
    र
    1.09
    ｅ
    1.08
     марта
    1.05
     can
    1.05
    Ò
    1.04
     км
    1.03
    Activations Density 0.043%

    No Known Activations