© 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. 129185
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on standalone numeric tokens (sequences of digits), effectively detecting numbers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    citation identifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     elektrische
    -1.35
    enseignements
    -1.32
     estrena
    -1.23
     construite
    -1.13
    為に
    -1.13
     größe
    -1.11
     ™
    -1.09
     praktische
    -1.09
     シール
    -1.05
     vorige
    -1.05
    POSITIVE LOGITS
     these
    1.41
     their
    1.40
     other
    1.30
     even
    1.30
     any
    1.23
     it
    1.22
     three
    1.16
    ಔ
    1.16
     unrelenting
    1.15
     whose
    1.13
    Activations Density 0.001%

    No Known Activations