© 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. 67951
    Prev
    Next
    INDEX
    Explanations

    html includes, The antenatal, In pictures, Optical fibers

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

    the HTML element marker ".html" in webpage code.

    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
     only
    -1.28
     además
    -1.00
    𝘮
    -0.94
    crania
    -0.90
     września
    -0.90
    ．．
    -0.89
    
    -0.89
     isn
    -0.85
     Interess
    -0.85
    TestBase
    -0.85
    POSITIVE LOGITS
    一丝
    1.04
    疋
    1.03
     runes
    1.02
     napis
    1.01
    我了
    1.01
     אָ
    1.00
    شوند
    0.98
     novamente
    0.98
    Якщо
    0.96
    هدف
    0.95
    Activations Density 0.000%

    No Known Activations