© 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. 9467
    Prev
    Next
    INDEX
    Explanations

    and connecting clauses

    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
     火鍋
    -1.15
     herbes
    -1.11
     ciment
    -1.10
     ſol
    -1.09
    猊
    -1.05
    Hombre
    -1.05
     広場
    -1.04
     trouva
    -1.03
    personen
    -1.03
     siè
    -1.02
    POSITIVE LOGITS
     to
    1.16
     Y
    1.14
     can
    1.13
     practical
    1.12
     U
    1.08
     p
    1.06
     n
    1.05
     Lo
    1.05
     it
    1.04
     O
    1.03
    Activations Density 0.068%

    No Known Activations