© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35011
    Prev
    Next
    INDEX
    Explanations

    code and technical vocabulary

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

    The neuron activates on programming identifiers (like variable, function, class, or other code symbols).

    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
     still
    -1.29
    Ứng
    -1.20
    Ưu
    -1.14
     anderen
    -1.03
     autres
    -1.03
    return
    -1.02
     enkele
    -1.00
     /
    -0.99
     \
    -0.98
    ⊖
    -0.98
    POSITIVE LOGITS
    .}(
    1.21
     doté
    1.03
     by
    1.03
    шого
    1.01
     documental
    1.00
    着脸
    1.00
    bemos
    0.98
     (
    0.98
     argumentos
    0.98
    你是不是
    0.96
    Activations Density 0.002%

    No Known Activations