© 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. 104431
    Prev
    Next
    INDEX
    Explanations

    IRS Letter, abbreviations, testing terms

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ······
    -1.29
     poë
    -1.26
     francia
    -1.26
     vuitton
    -1.24
     tami
    -1.23
     fú
    -1.23
    aning
    -1.23
    ̳
    -1.21
     ára
    -1.20
    konos
    -1.20
    POSITIVE LOGITS
     but
    1.68
     and
    1.66
     to
    1.56
     that
    1.22
     will
    1.16
     always
    1.15
     is
    1.11
     never
    1.06
    乃是
    1.05
     too
    1.05
    Activations Density 0.003%

    No Known Activations