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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 110826
    Prev
    Next
    INDEX
    Explanations

    glandular structure/region/tissue

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

    nouns that refer to specific structures or containers like cupboards, glandular regions, and blunders.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    錞
    -2.97
     ที่
    -2.66
    e
    -2.53
     ใน
    -2.39
    F
    -2.38
    噲
    -2.30
     是
    -2.28
    籥
    -2.25
    躄
    -2.25
     และ
    -2.23
    POSITIVE LOGITS
    riezmann
    2.63
    结语
    2.34
     we
    2.34
     remnants
    2.33
     tomando
    2.16
     esigen
    2.16
    之間
    2.11
    缈
    2.09
     asegurarse
    2.05
     vollständ
    2.03
    Activations Density 0.002%

    No Known Activations