© 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. 129748
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on numeric literals (numbers) in the code.

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

    code snippets and configuration

    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
     as
    -1.40
    などを
    -1.34
     several
    -1.22
    ？』
    -1.17
     before
    -1.17
     various
    -1.16
     make
    -1.15
    そして
    -1.13
     some
    -1.13
     in
    -1.10
    POSITIVE LOGITS
    荑
    1.11
     dispuestos
    1.06
    を書く
    1.04
    の方も
    1.04
     lì
    1.04
     riesgos
    1.03
     nct
    1.00
    の為
    0.99
    ようになった
    0.98
     puertos
    0.98
    Activations Density 0.025%

    No Known Activations