© 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. 71078
    Prev
    Next
    INDEX
    Explanations

    mathematical numbers

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

    The neuron is selectively activated by multi‐digit numeric tokens (long sequences of 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
     in
    -1.71
    しましたが
    -1.46
     after
    -1.38
     pengobatan
    -1.30
     perla
    -1.28
     comerci
    -1.27
     while
    -1.27
    utuhan
    -1.25
     pistola
    -1.24
     boxe
    -1.23
    POSITIVE LOGITS
     such
    1.46
    に入れる
    1.46
     dessa
    1.45
     chamado
    1.42
     verschillende
    1.40
     этих
    1.36
     llenos
    1.34
     cómodo
    1.32
     pojawia
    1.30
     świąte
    1.30
    Activations Density 0.005%

    No Known Activations