© 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. 72323
    Prev
    Next
    INDEX
    Explanations

    code structures and parameters

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

    The neuron is specialized to pick out numeric literals (integers or decimals) 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
     first
    -1.50
     different
    -1.20
     only
    -1.20
     those
    -1.13
     all
    -1.11
     when
    -1.10
     ONLY
    -0.98
    Caracteristici
    -0.98
     Since
    -0.96
    When
    -0.93
    POSITIVE LOGITS
     estadounid
    1.19
     auront
    1.18
    TestTools
    1.05
    菒
    1.02
     eccl
    1.02
     pourront
    1.02
     ofrece
    1.02
     продол
    1.02
     yaklaşık
    1.00
    Léon
    1.00
    Activations Density 0.025%

    No Known Activations