© 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. 34209
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and code

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

    The neuron activates specifically on numeric literals and loop‐control tokens (e.g. numbers, the “for” index, “=”, “:”) in code snippets.

    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
    ÈNE
    -1.42
     bağlantılar
    -1.41
     trouvent
    -1.33
    ଘ
    -1.31
    Créditos
    -1.31
    ENODEV
    -1.30
    Vídeo
    -1.27
     имму
    -1.26
     Biaya
    -1.23
    طريقة
    -1.23
    POSITIVE LOGITS
    (
    1.53
     at
    1.23
     макия
    1.23
    ଵ
    1.23
     къде
    1.21
     their
    1.20
    /
    1.20
     previous
    1.16
     which
    1.14
     katika
    1.14
    Activations Density 0.019%

    No Known Activations