© 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. 25923
    Prev
    Next
    INDEX
    Explanations

    counting and summation in code

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

    This neuron fires on numeric literal tokens (number constants) 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
     information
    -1.09
    Ilustra
    -0.93
    Nguy
    -0.91
    },[])
    -0.91
    Erfahrung
    -0.88
    образие
    -0.87
     creating
    -0.86
     destinations
    -0.85
     información
    -0.85
     Würde
    -0.85
    POSITIVE LOGITS
     quantit
    1.12
     counting
    1.06
    计算
    1.05
     сум
    1.00
     calcula
    1.00
    CRYPTO
    0.98
    tab
    0.97
     sum
    0.97
     estimate
    0.96
     calculate
    0.96
    Activations Density 0.011%

    No Known Activations