© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67289
    Prev
    Next
    INDEX
    Explanations

    medical procedures and treatments

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

    medical procedures ending with "plasty" such as valvuloplasty, angioplasty, and vertebroplasty.

    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_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
     are
    -1.31
     couvrir
    -1.14
     I
    -1.09
     MUCH
    -1.07
     blaue
    -1.05
     höchste
    -1.02
     hochwertige
    -1.02
     bouw
    -0.99
     spezielle
    -0.99
     ue
    -0.98
    POSITIVE LOGITS
     successfully
    1.43
     cantora
    1.39
     method
    1.28
     before
    1.27
    成功
    1.23
     or
    1.23
    ֵּ
    1.23
     without
    1.21
     방법
    1.19
    lasyon
    1.18
    Activations Density 0.355%

    No Known Activations