© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127729
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on occurrences of the verbs “see” or “seen” (and similar forms of “see”).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    perceived or seen locations/context

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Negative Logits
     a
    -2.34
    すみません
    -1.75
    糴
    -1.67
    さぁ
    -1.65
    明日は
    -1.65
    えっ
    -1.61
     ܙ
    -1.55
    ごめん
    -1.52
    あぁ
    -1.51
    魠
    -1.49
    POSITIVE LOGITS
     in
    3.36
     from
    3.20
     on
    2.73
     at
    1.98
     before
    1.84
     during
    1.84
     with
    1.62
     throughout
    1.62
     by
    1.55
     within
    1.54
    Activations Density 0.022%

    No Known Activations