© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 69642
    Prev
    Next
    INDEX
    Explanations

    Wigan, Orwell, Corporal, hydrochloride, carbide

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

    terms related to professional sports teams and technical materials, particularly "Wigan" and "carbide."

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

    The neuron fires on proper‐name or domain‐specific noun tokens (places, team names, class names, chemical compounds, etc.).

    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
    '
    -5.44
    ’
    -3.27
    (
    -3.03
     
    -2.95
     Then
    -2.77
    л
    -2.73
    —
    -2.73
    2
    -2.73
    -2.70
    きちんと
    -2.61
    POSITIVE LOGITS
    ⡪
    3.27
    鸱
    3.19
    鯔
    3.16
    鷓
    3.16
    揠
    3.11
    ჻
    3.00
    𓋼
    2.97
    ﹍﹍
    2.97
    ቍ
    2.95
    ingtones
    2.86
    Activations Density 0.010%

    No Known Activations