© 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. 105970
    Prev
    Next
    INDEX
    Explanations

    recognize something/someone

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

    The neuron activates on occurrences of the verb “recognize” (including variant spellings).

    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
     $\
    -1.93
     estos
    -1.70
     $
    -1.66
     "
    -1.58
    <bos>
    -1.54
     to
    -1.46
     When
    -1.43
     so
    -1.41
     FOR
    -1.41
     just
    -1.38
    POSITIVE LOGITS
    禇
    1.85
     nerf
    1.70
     reconnaître
    1.63
     kalender
    1.62
    月から
    1.61
    ㎉
    1.59
    畱
    1.55
     Tiga
    1.55
     viata
    1.52
     visage
    1.51
    Activations Density 0.025%

    No Known Activations