© 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. 13608
    Prev
    Next
    INDEX
    Explanations

    numbers around punctuation

    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
     насле
    -1.10
     marron
    -1.07
    ANTED
    -1.05
    ilerini
    -1.05
    ПЕ
    -1.05
     romero
    -1.05
     vian
    -1.04
     måneder
    -1.03
     loto
    -1.02
     loup
    -1.02
    POSITIVE LOGITS
     others
    1.16
     that
    1.11
     whether
    1.09
     its
    1.08
     you
    1.05
     of
    1.05
     &
    1.03
    as
    1.02
    are
    1.02
     as
    1.01
    Activations Density 0.067%

    No Known Activations