© 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. 95529
    Prev
    Next
    INDEX
    Explanations

    Question prefixes and code structures

    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
     by
    -2.06
     it
    -1.87
     not
    -1.64
     on
    -1.58
     from
    -1.55
     several
    -1.55
     does
    -1.48
     without
    -1.48
     many
    -1.41
     most
    -1.40
    POSITIVE LOGITS
     Dinas
    1.45
     .......
    1.44
     Quando
    1.37
     REALLY
    1.34
     การ
    1.34
     .........
    1.33
    igth
    1.31
     ww
    1.30
     NEW
    1.28
     새로운
    1.27
    Activations Density 0.001%

    No Known Activations