© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 59731
    Prev
    Next
    INDEX
    Explanations

    past participle following auxiliary verbs

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

    The neuron lights up on specialized technical or scientific terms—typically long, domain-specific nouns or jargon used in scholarly or technical writing.

    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
    тились
    -1.30
    }
    -1.27
    klü
    -1.27
     []:
    -1.20
     alebo
    -1.16
    (!__
    -1.16
     합니다
    -1.16
     contrôler
    -1.15
     Way
    -1.15
    >';
    -1.14
    POSITIVE LOGITS
     (
    1.64
    そういった
    1.40
    cracy
    1.33
     comprendere
    1.30
     you
    1.24
     completas
    1.20
    =>"
    1.19
    нуть
    1.19
     pneu
    1.18
     him
    1.17
    Activations Density 0.782%

    No Known Activations