© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 9630
    Prev
    Next
    INDEX
    Explanations

    class names and types

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

    This neuron detects the names of imported classes or types (capitalized identifiers) in import/use statements.

    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
     besonderes
    -1.23
     for
    -1.23
     particular
    -1.22
    髭
    -1.20
     Preisen
    -1.18
    bandcamp
    -1.16
    tvguide
    -1.10
     Briefe
    -1.09
     persön
    -1.08
     numerosi
    -1.08
    POSITIVE LOGITS
     that
    1.59
    焢
    1.34
     répon
    1.31
     Kalimantan
    1.30
    ابراین
    1.28
    sieme
    1.25
     AppCompatTheme
    1.22
    quelize
    1.22
    潜力
    1.21
     """",
    1.20
    Activations Density 0.021%

    No Known Activations