© 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. 124689
    Prev
    Next
    INDEX
    Explanations

    medical conditions and terms

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

    medical terminology related to anatomy, specifically bone, joint, and tendon conditions.

    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
     to
    -2.02
    撂
    -1.59
    捅
    -1.43
     муки
    -1.35
    给他们
    -1.34
     autorisation
    -1.33
     dct
    -1.30
    攥
    -1.29
    哽
    -1.26
    ごとに
    -1.24
    POSITIVE LOGITS
     many
    1.51
    ࿚
    1.43
    beyaz
    1.40
    Polecam
    1.40
     bebés
    1.40
     when
    1.39
    Bardzo
    1.37
    埛
    1.37
     Handeln
    1.37
    Może
    1.36
    Activations Density 0.723%

    No Known Activations