© 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. 102252
    Prev
    Next
    INDEX
    Explanations

    end of list item

    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
     permit
    -1.34
    なども
    -1.32
     каждом
    -1.31
    ぐれ
    -1.28
     égard
    -1.27
    亖
    -1.27
     таком
    -1.26
     tandis
    -1.25
     success
    -1.23
     للح
    -1.23
    POSITIVE LOGITS
     a
    1.94
     an
    1.70
     penghar
    1.57
     the
    1.56
     pengobatan
    1.55
     pemeriksaan
    1.53
     prêtre
    1.44
     who
    1.42
     शुर
    1.41
     keperluan
    1.40
    Activations Density 0.046%

    No Known Activations