© 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. 54078
    Prev
    Next
    INDEX
    Explanations

    sporting events and decisions

    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
     其他
    -1.16
     gron
    -1.07
    Flutter
    -1.07
     cukru
    -1.04
    当场
    -1.02
     jati
    -1.01
     дости
    -1.00
     of
    -1.00
     poliester
    -1.00
     brie
    -0.99
    POSITIVE LOGITS
     before
    1.32
     on
    1.23
    ὺς
    1.21
     first
    1.16
     allowing
    1.13
     any
    1.11
    ydın
    1.09
    地说
    1.09
     when
    1.09
     if
    1.09
    Activations Density 0.004%

    No Known Activations