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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 14235
    Prev
    Next
    INDEX
    Explanations

    lists of dates, case studies, and questions

    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
     hunde
    -1.34
    沵
    -1.33
     dekoratif
    -1.32
    雰囲
    -1.27
     organik
    -1.27
    푁
    -1.27
     aktar
    -1.24
     kollu
    -1.23
    Ᏹ
    -1.23
    Осно
    -1.23
    POSITIVE LOGITS
     to
    1.66
     of
    1.24
    !
    1.22
     both
    1.20
     where
    1.15
     those
    1.15
     that
    1.13
     what
    1.12
    ?
    1.11
     just
    1.05
    Activations Density 0.000%

    No Known Activations