© 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. 74930
    Prev
    Next
    INDEX
    Explanations

    role in things

    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
    の詳細
    -1.23
     muere
    -1.22
    Více
    -1.17
    鑁
    -1.14
     acompaña
    -1.14
     melalui
    -1.13
     añade
    -1.11
     resultaat
    -1.09
     uitgenodigd
    -1.09
     pendientes
    -1.09
    POSITIVE LOGITS
     success
    1.46
     overall
    1.38
     because
    1.21
     equation
    1.19
     understanding
    1.16
     negotiations
    1.16
     getting
    1.16
     (
    1.15
     both
    1.13
     calculations
    1.09
    Activations Density 0.111%

    No Known Activations