© 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. 14798
    Prev
    Next
    INDEX
    Explanations

    "pretty" + adjective

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

    The neuron detects the adverb “pretty” (and its capitalized form) used as an 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
    ৢ
    -2.38
    は
    -2.34
     of
    -2.31
    
    -2.27
    嫆
    -2.25
    ㉕
    -2.20
    卺
    -2.08
    la
    -2.05
    ↵
    -2.03
    饧
    -2.02
    POSITIVE LOGITS
     zelve
    2.39
    んですが
    2.14
    Despite
    2.13
     twij
    2.11
    になりたい
    2.03
    つづく
    2.02
    ところに
    1.95
     darn
    1.95
    rlrl
    1.95
    Although
    1.93
    Activations Density 0.009%

    No Known Activations