© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 27257
    Prev
    Next
    INDEX
    Explanations

    we find provides tested

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

    The neuron activates on numeric and punctuation tokens (digits, parentheses, periods) characteristic of citations, section labels, and statistical notation in academic texts.

    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
    Enregistrer
    -1.73
     النبات
    -1.52
     иллюстрация
    -1.38
     ܐ
    -1.38
    ֺ
    -1.37
     растения
    -1.35
    ὸς
    -1.34
     anún
    -1.30
     शरीर
    -1.30
    Spécification
    -1.29
    POSITIVE LOGITS
     we
    1.96
    וּ
    1.70
     our
    1.66
    我们
    1.61
    年から
    1.48
     Alternative
    1.47
    เรา
    1.45
    丁目
    1.42
    וֹ
    1.41
     бампер
    1.41
    Activations Density 0.062%

    No Known Activations