© 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. 10-GEMMASCOPE-RES-131K
    7. 65591
    Prev
    Next
    INDEX
    Explanations

    slick descriptions

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

    The neuron fires on occurrences of the substring “slick” (in any casing or inflection).

    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
    on
    -3.36
     they
    -2.52
    of
    -2.48
     benö
    -2.39
    он
    -2.38
     bewilder
    -2.31
    In
    -2.31
    in
    -2.30
     i
    -2.25
    ありますが
    -2.22
    POSITIVE LOGITS
    屙
    2.91
    뿅
    2.78
     When
    2.78
    i
    2.72
     berdua
    2.70
    鷙
    2.70
    涠
    2.66
    鈇
    2.63
    навли
    2.61
    い
    2.59
    Activations Density 0.002%

    No Known Activations