© 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. 22-GEMMASCOPE-RES-131K
    7. 13041
    Prev
    Next
    INDEX
    Explanations

    bloodstream infections, touchscreen, linewidth

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

    The neuron selectively activates on long, multi-syllabic nouns—often compound or technical terms.

    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
    }
    -2.45
     или
    -2.34
     :
    -2.30
     The
    -2.28
    𝖕
    -2.13
     "'",
    -2.11
     \
    -2.02
    ⚋
    -2.02
     Your
    -2.00
    garmin
    -2.00
    POSITIVE LOGITS
     để
    3.00
    Skocz
    2.91
    to
    2.75
    namental
    2.72
    welli
    2.67
    
    2.45
     να
    2.44
     глазах
    2.39
     кухне
    2.36
    媄
    2.36
    Activations Density 0.506%

    No Known Activations