© 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. 58875
    Prev
    Next
    INDEX
    Explanations

    becoming mainstream

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

    This neuron chiefly responds to common function words—especially high‐frequency prepositions, conjunctions, and other grammatical connectors.

    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
     сообщили
    -2.45
     detalló
    -2.25
     сообщил
    -2.20
     indicó
    -2.11
     médec
    -2.09
     illustratie
    -2.05
     艺术
    -2.02
    ֶּ
    -1.99
    sikker
    -1.99
    ּוֹ
    -1.99
    POSITIVE LOGITS
     повече
    2.13
     дѣ
    1.83
     крепления
    1.77
     ихъ
    1.75
     Erziehung
    1.71
     galletas
    1.69
     экрана
    1.69
     japones
    1.68
     vegetales
    1.67
     встроен
    1.67
    Activations Density 0.748%

    No Known Activations