© 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. 10-GEMMASCOPE-RES-131K
    7. 13540
    Prev
    Next
    INDEX
    Explanations

    species names with scientific classifications

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

    scientific species names with the specific epithet ending in 'ii'.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects instances of the Roman numeral “II” (in lowercase or uppercase) appearing as a suffix or section label.

    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
     whats
    -1.45
     how
    -1.41
    ต่างๆ
    -1.35
     داره
    -1.34
    屃
    -1.33
     slaugh
    -1.33
     its
    -1.31
    をご覧ください
    -1.28
     what
    -1.27
     Panchayat
    -1.27
    POSITIVE LOGITS
    Initially
    1.47
     faisaient
    1.30
    <0xEF>
    1.27
    Forrás
    1.26
    ナブル
    1.25
    ‧
    1.25
     sejak
    1.23
     ложки
    1.23
     '_
    1.23
    Our
    1.23
    Activations Density 0.038%

    No Known Activations