© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 19383
    Prev
    Next
    INDEX
    Explanations

    find

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

    The neuron strongly detects occurrences of the verb “find” (and its inflected form “finding”).

    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
    ᚔ
    -1.41
    Kapitel
    -1.33
     נגד
    -1.32
     家族
    -1.23
    ไป
    -1.20
     errone
    -1.20
    硚
    -1.18
     contextLoads
    -1.18
    訃
    -1.17
    مقال
    -1.16
    POSITIVE LOGITS
     in
    1.61
     such
    1.41
     would
    1.34
     new
    1.29
     on
    1.28
    %
    1.22
    useNewUrlParser
    1.20
     with
    1.13
     Kró
    1.13
     any
    1.12
    Activations Density 0.084%

    No Known Activations