© 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. 10-GEMMASCOPE-RES-131K
    7. 72784
    Prev
    Next
    INDEX
    Explanations

    geometric shapes and technical terms

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

    The neuron primarily fires on technical or mathematical jargon—specialized terms you’d see in scientific papers, patents, or geometry/math discussions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ͆
    -1.12
     Redacción
    -1.08
     demostra
    -1.08
     zwierzę
    -1.08
     in
    -1.07
     miscellaneous
    -1.05
     nesse
    -1.03
     använda
    -1.02
    millan
    -1.01
     همچ
    -1.01
    POSITIVE LOGITS
     già
    1.19
     himo
    1.18
     suna
    1.11
     их
    1.07
     cartier
    1.05
    ⡞
    1.04
     kabupaten
    1.03
    哢
    1.03
     raso
    1.02
    ינוך
    1.02
    Activations Density 0.635%

    No Known Activations