© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116015
    Prev
    Next
    INDEX
    Explanations

    int, Range, push, make

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

    The neuron flags programming identifiers—especially type names and standard-library function or class names 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_34/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
     Object
    -0.78
    ĵ
    -0.75
    чах
    -0.70
     streamlined
    -0.69
     sputum
    -0.68
    aspectRatio
    -0.68
     every
    -0.67
    يران
    -0.67
    jewish
    -0.66
    이스
    -0.65
    POSITIVE LOGITS
    lazy
    1.32
    区间
    1.19
     lazy
    1.17
     업
    1.09
     updates
    1.03
    update
    1.02
     update
    1.00
    Lazy
    0.99
    區
    0.99
    propagate
    0.97
    Activations Density 0.001%

    No Known Activations