© 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. 69041
    Prev
    Next
    INDEX
    Explanations

    citation and year in parentheses

    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
     of
    -1.59
     by
    -1.54
     to
    -1.48
     as
    -1.47
     from
    -1.34
     we
    -1.26
     I
    -1.25
     in
    -1.25
    :
    -1.19
     also
    -1.16
    POSITIVE LOGITS
    Karakteristik
    1.54
    Akan
    1.48
    Karakter
    1.45
    Gele
    1.41
    Seni
    1.38
    Hanya
    1.38
    Kelebihan
    1.38
    معرفی
    1.36
    Merhaba
    1.36
    Ilustra
    1.32
    Activations Density 0.001%

    No Known Activations