© 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. 71994
    Prev
    Next
    INDEX
    Explanations

    OT or ij

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

    The neuron activates on tokens containing the exact uppercase letters “OT,” typically as part of alphanumeric codes or identifiers.

    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
    ة
    -2.75
     They
    -2.53
    ߹
    -2.36
    ing
    -2.34
     To
    -2.27
    ING
    -2.25
    翼翼
    -2.17
    ा
    -2.06
     peristiwa
    -2.05
     Of
    -2.00
    POSITIVE LOGITS
    {
    2.98
    enablog
    2.61
     patienter
    2.36
    d
    2.36
    en
    2.34
     davran
    2.34
    aa
    2.28
    ia
    2.28
    re
    2.27
    al
    2.27
    Activations Density 0.006%

    No Known Activations