© 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. 10-GEMMASCOPE-RES-131K
    7. 45450
    Prev
    Next
    INDEX
    Explanations

    while in or on

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

    The neuron fires strongly on occurrences of “in” immediately followed by a numeral (e.g. “in 264,” “in 258,” etc.), marking “in <number>” constructions.

    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
    Negative Logits
     
    -2.19
    </h5>
    -1.91
    の前に
    -1.75
     cruzado
    -1.66
     yardımcı
    -1.66
     méret
    -1.65
     juzgar
    -1.63
     rencont
    -1.61
    şağı
    -1.60
    だったので
    -1.56
    POSITIVE LOGITS
    9
    1.80
    5
    1.70
    8
    1.69
     ſta
    1.68
    </strong>
    1.66
    The
    1.66
    秋天
    1.58
    7
    1.58
     豪
    1.51
     For
    1.48
    Activations Density 0.009%

    No Known Activations