© 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. 65628
    Prev
    Next
    INDEX
    Explanations

    programming code constructs

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

    The neuron activates on numeric literal tokens (e.g., integer or floating‐point constants) 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
     genügend
    -1.00
     other
    -0.99
     then
    -0.94
     ausreichend
    -0.93
     ఈ
    -0.88
    밈
    -0.88
     betrieben
    -0.88
    vw
    -0.86
     altre
    -0.85
     erzeugt
    -0.84
    POSITIVE LOGITS
     their
    1.28
     (
    1.18
     in
    1.02
    fromDate
    0.98
    łącz
    0.95
    hloro
    0.94
     and
    0.93
    ),(
    0.91
     problemer
    0.90
     måned
    0.87
    Activations Density 0.020%

    No Known Activations