© 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. 118804
    Prev
    Next
    INDEX
    Explanations

    superficially, setFocusable, Fielder

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

    the word "superficially" or text containing technical/scientific content with specific formatting patterns.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron activates on occurrences of the root “superfic” (as in “superficial” or “superficially”).

    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
    ra
    -2.66
     they
    -2.48
    屃
    -2.23
    It
    -2.20
    ра
    -2.20
    ◆◆
    -2.19
    鯓
    -2.19
    ࿙
    -2.17
    la
    -2.16
    妡
    -2.08
    POSITIVE LOGITS
    0
    3.38
    d
    2.75
     теми
    2.63
    6
    2.63
     мы
    2.53
    主要是
    2.47
     seus
    2.47
     breezy
    2.45
     Wszyst
    2.41
    蓐
    2.41
    Activations Density 0.000%

    No Known Activations