© 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. 22-GEMMASCOPE-RES-131K
    7. 67028
    Prev
    Next
    INDEX
    Explanations

    Virginia activity chromatography gasoline billion

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

    This neuron responds to technical or scientific terminology—especially subword fragments of specialized jargon in scientific, engineering, and academic contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     there
    -2.13
     only
    -1.86
     at
    -1.80
     these
    -1.73
     from
    -1.73
     one
    -1.58
     other
    -1.58
     on
    -1.51
     you
    -1.49
     to
    -1.46
    POSITIVE LOGITS
    rée
    1.55
     fidé
    1.54
     hés
    1.48
    蚰
    1.48
    formatie
    1.48
    terscotch
    1.47
     caricatura
    1.46
    ereo
    1.45
     desinf
    1.45
     plafon
    1.43
    Activations Density 0.271%

    No Known Activations