© 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. 73572
    Prev
    Next
    INDEX
    Explanations

    same or best thing

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

    The neuron mainly fires on words that express exactness, equality, or extremeness (e.g. “same,” “exact,” “correct,” “best,” “difference”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    Not in Any Lists

    No Comments

    Negative Logits
    えっ
    -1.92
    すっ
    -1.77
    うわ
    -1.74
    凄く
    -1.70
    つづく
    -1.68
    をかける
    -1.63
    なかな
    -1.62
     wondrous
    -1.61
    ビックリ
    -1.61
     VERY
    -1.57
    POSITIVE LOGITS
     although
    2.47
     because
    2.30
     when
    2.30
     while
    2.14
     after
    2.00
     including
    2.00
     until
    1.98
     which
    1.97
     may
    1.94
     before
    1.92
    Activations Density 0.054%

    No Known Activations