© 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. 64639
    Prev
    Next
    INDEX
    Explanations

    technical terms and specifications

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

    The neuron responds selectively to long, multi-syllabic technical or scientific terms (e.g. specialized jargon).

    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
    を
    -2.30
    が
    -2.28
     Grüßen
    -2.20
    ,
    -2.20
    と
    -2.16
    は
    -2.08
    '
    -2.06
    參考文獻
    -1.98
    <bos>
    -1.88
    d
    -1.80
    POSITIVE LOGITS
    corrhi
    3.20
    の方に
    2.88
    久し
    2.63
    ほら
    2.61
    あぁ
    2.59
    感じが
    2.50
    為に
    2.48
    あー
    2.47
    様な
    2.44
    ところに
    2.39
    Activations Density 5.008%

    No Known Activations