© 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. 128813
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric tokens (i.e. multi-digit numbers).

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

    parenthetical lists and numbering

    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
     OGSÅ
    -1.18
    FUENTES
    -1.17
    CONTENIDO
    -1.12
    CONCLUSIONES
    -1.12
    CAPITULO
    -1.11
     kabát
    -1.09
    」,
    -1.09
    Would
    -1.09
    NOWLED
    -1.07
    ШИ
    -1.07
    POSITIVE LOGITS
     second
    1.22
    1
    1.19
     two
    1.15
    2
    1.10
     but
    1.10
     A
    1.04
     three
    1.01
     on
    1.01
     fifth
    1.01
     –
    1.00
    Activations Density 0.008%

    No Known Activations