© 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. 73379
    Prev
    Next
    INDEX
    Explanations

    code and programming concepts

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

    The neuron fires most strongly on programming-related identifiers—class/module names, library/framework tokens, and other technical symbols 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
     their
    -1.35
     all
    -1.23
     Uniwers
    -1.20
     still
    -1.15
     camisas
    -1.13
    ssä
    -1.08
     chère
    -1.08
     jika
    -1.07
     meticulously
    -1.07
     milho
    -1.06
    POSITIVE LOGITS
    你不要
    1.23
    along
    1.13
    Hilsen
    1.09
     همچنین
    1.07
    なるべく
    1.05
     dunque
    1.03
    綺麗な
    1.02
    -
    1.02
     şun
    1.02
     afore
    1.02
    Activations Density 0.030%

    No Known Activations