© 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. 129475
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on multi‐digit numeric tokens.

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

    Q: or name start

    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
     rése
    -1.30
     TÉ
    -1.12
     bleu
    -1.11
    蟶
    -1.09
     vinagre
    -1.09
     revoir
    -1.08
     vernis
    -1.06
     podamos
    -1.05
     peinado
    -1.05
     Très
    -1.04
    POSITIVE LOGITS
    \|_{
    1.13
     could
    1.07
     will
    1.05
     or
    1.04
     certainly
    1.00
     defined
    0.98
     would
    0.98
     also
    0.98
     cannot
    0.96
     may
    0.95
    Activations Density 0.000%

    No Known Activations