© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74464
    Prev
    Next
    INDEX
    Explanations

    television series

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

    The neuron strongly activates on relatively uncommon, content‐bearing words (specialized nouns, verbs, and adjectives) rather than on high‐frequency function words.

    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
     many
    -1.63
     its
    -1.59
    HN
    -1.27
    </sup>
    -1.23
    r
    -1.20
    ͌
    -1.20
    it
    -1.20
    o
    -1.15
    v
    -1.13
    ª
    -1.12
    POSITIVE LOGITS
    Ibu
    1.26
     beteken
    1.23
     membantu
    1.21
    Eater
    1.17
     dieß
    1.16
    
    1.15
    ⁈
    1.14
     durumda
    1.13
     `"
    1.13
     svého
    1.13
    Activations Density 0.233%

    No Known Activations