© 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. 129408
    Prev
    Next
    INDEX
    Explanations

    This neuron activates on numeric literals in code—especially numbers appearing in `#include` or template/include‐style directives.

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

    programming imports and phrases

    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
     kompeti
    -1.15
     hotelu
    -1.13
     perfekt
    -1.12
     katastro
    -1.11
    bedien
    -1.10
    stande
    -1.06
     méda
    -1.05
     klare
    -1.05
     Accessoires
    -1.05
    enance
    -1.05
    POSITIVE LOGITS
     at
    1.12
     might
    1.02
    4
    0.94
     also
    0.93
     (
    0.92
     should
    0.91
     often
    0.91
    l
    0.90
     outlining
    0.90
     probably
    0.90
    Activations Density 0.000%

    No Known Activations