© 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. 38525
    Prev
    Next
    INDEX
    Explanations

    intensifiers like very, pretty, really

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

    The neuron fires on common intensifier words and adverbs (e.g. “very,” “pretty,” “much,” “lot,” etc.) that express degree or emphasis.

    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
     étan
    -1.26
     pakan
    -1.24
     teknologi
    -1.23
     ciclismo
    -1.23
     konsep
    -1.22
     sekunder
    -1.22
    🧌
    -1.21
     fusil
    -1.18
     maksimal
    -1.14
     météoro
    -1.14
    POSITIVE LOGITS
    為に
    1.13
     like
    1.12
    ようです
    1.11
    ところに
    1.06
     aantal
    1.05
    ที่จะ
    1.05
     arbejde
    1.05
     compared
    1.01
     展望
    1.00
    ときは
    0.99
    Activations Density 0.025%

    No Known Activations