© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130265
    Prev
    Next
    INDEX
    Explanations

    The neuron selectively fires on numeric tokens—sequences of digits (e.g. literal numbers or digit‐heavy identifiers).

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

    `All relevant`, `The present`, `Q:`, `Posts tagged`

    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
     declaração
    -1.20
     autoridade
    -1.13
     Aéroport
    -1.12
     puntata
    -1.12
     collaborazione
    -1.09
     attesa
    -1.08
     beelden
    -1.08
     AFFAIRS
    -1.05
     sufrió
    -1.04
     igreja
    -1.03
    POSITIVE LOGITS
     use
    1.23
     (
    1.23
    get
    1.14
     or
    1.13
     b
    1.11
     by
    1.10
     get
    1.07
    conceito
    1.06
     .
    1.03
     c
    1.02
    Activations Density 0.000%

    No Known Activations