© 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. 73882
    Prev
    Next
    INDEX
    Explanations

    css emphasis and scope

    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
     to
    -1.38
     Před
    -1.35
    centerTitle
    -1.33
     were
    -1.29
     artesanato
    -1.27
     of
    -1.25
    ukunfts
    -1.19
    cookieParser
    -1.19
     instala
    -1.19
     intér
    -1.19
    POSITIVE LOGITS
    You
    1.63
    However
    1.52
    Because
    1.43
    These
    1.41
    That
    1.39
    Since
    1.33
    Instead
    1.32
    Despite
    1.28
    Here
    1.26
    Also
    1.25
    Activations Density 0.001%

    No Known Activations