© 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. 10-GEMMASCOPE-RES-131K
    7. 156
    Prev
    Next
    INDEX
    Explanations

    all, any, every

    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_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
     igualmente
    -1.44
    ྜ
    -1.41
    }]{
    -1.31
     TBD
    -1.30
    gebob
    -1.29
     in
    -1.27
     and
    -1.25
    }.
    -1.24
    gemä
    -1.18
    "/>
    -1.17
    POSITIVE LOGITS
    肮
    1.39
    わけで
    1.33
     welches
    1.31
     which
    1.24
     rechange
    1.23
     people
    1.23
     केवल
    1.21
    惴
    1.19
    樣的
    1.19
    Langkah
    1.19
    Activations Density 0.064%

    No Known Activations