© 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. 26450
    Prev
    Next
    INDEX
    Explanations

    C++ syntax

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

    The neuron activates on numeric literals (sequences of digits) in code.

    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
     herbe
    -1.49
     poë
    -1.45
     mense
    -1.38
     pittores
    -1.38
     pistolet
    -1.37
     décontract
    -1.35
     faciliter
    -1.35
    groet
    -1.30
     {
    -1.30
     horloge
    -1.29
    POSITIVE LOGITS
     and
    1.48
     -
    1.44
     on
    1.30
     /
    1.17
     had
    1.17
     both
    1.17
    ?
    1.16
     establish
    1.15
     there
    1.14
    It
    1.14
    Activations Density 0.033%

    No Known Activations