© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 28066
    Prev
    Next
    INDEX
    Explanations

    foreign language fragments

    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
     as
    -1.26
     get
    -1.23
     all
    -1.21
     on
    -1.16
     with
    -1.12
     becomes
    -1.11
     to
    -1.08
     give
    -1.07
     gives
    -1.06
     gets
    -1.06
    POSITIVE LOGITS
    -*
    1.28
    '~
    1.18
     commerciaux
    1.14
    ishe
    1.09
     vijf
    1.09
     siè
    1.08
     stück
    1.08
     Capacidad
    1.07
    -&
    1.07
     manly
    1.07
    Activations Density 0.055%

    No Known Activations