© 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. 10-GEMMASCOPE-RES-131K
    7. 58736
    Prev
    Next
    INDEX
    Explanations

    relay race or team

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

    This neuron selectively fires on multi‐syllable proper names and specialized nouns (e.g. titles, technical terms, athlete names, event names).

    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
     দেখ
    -1.34
     thậm
    -1.34
    empres
    -1.29
    łyż
    -1.29
     mężczy
    -1.28
     edificios
    -1.26
     мои
    -1.26
     especially
    -1.24
    d
    -1.23
     мне
    -1.23
    POSITIVE LOGITS
     where
    1.63
    蔟
    1.44
    chaun
    1.37
    edì
    1.34
     emblema
    1.33
     umas
    1.31
    ionato
    1.30
     distante
    1.30
    halation
    1.27
     your
    1.24
    Activations Density 0.094%

    No Known Activations