© 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. 34-GEMMASCOPE-RES-131K
    7. 31011
    Prev
    Next
    INDEX
    Explanations

    function assignment

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

    This neuron detects numeric literals (numbers) 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_34/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
     aveug
    -0.90
    шься
    -0.90
     vya
    -0.90
    ccedil
    -0.87
    蛱
    -0.84
    рослав
    -0.82
    +.
    -0.82
     ещё
    -0.82
     déliv
    -0.82
     retrofit
    -0.81
    POSITIVE LOGITS
     with
    1.11
     and
    1.00
     such
    0.95
     simply
    0.94
     while
    0.91
    bagno
    0.90
    ituary
    0.88
    ونية
    0.87
     nėra
    0.87
     too
    0.85
    Activations Density 0.015%

    No Known Activations