© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 54236
    Prev
    Next
    INDEX
    Explanations

    quite followed by descriptors

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

    The neuron strongly activates on the adverb “quite,” detecting that specific intensifier.

    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
    ৢ
    -2.33
    辚
    -2.31
     Kategorien
    -2.09
    蠃
    -2.06
    蛱
    -2.05
    と
    -2.00
    烀
    -1.98
     gesamte
    -1.98
     dando
    -1.96
    皱眉
    -1.95
    POSITIVE LOGITS
     philosophie
    2.17
     geloof
    2.02
    饜
    2.00
    Despite
    1.99
    They
    1.98
    ‪.‬‬
    1.98
    Cartney
    1.95
    Although
    1.92
     pessoais
    1.85
    に使
    1.84
    Activations Density 0.009%

    No Known Activations