© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65892
    Prev
    Next
    INDEX
    Explanations

    intensification or border extension

    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
    鶺
    -1.58
     siè
    -1.45
     quai
    -1.43
    鵙
    -1.38
     incrí
    -1.36
     réfléchir
    -1.32
    킁
    -1.32
     utilisent
    -1.32
    EVERY
    -1.30
     suivent
    -1.29
    POSITIVE LOGITS
     as
    1.83
     at
    1.52
     may
    1.48
     in
    1.48
     by
    1.44
     for
    1.40
     with
    1.39
     some
    1.38
     sometimes
    1.37
     on
    1.34
    Activations Density 0.029%

    No Known Activations