© 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. 79802
    Prev
    Next
    INDEX
    Explanations

    end of sentence 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
     will
    -1.59
     you
    -1.43
     not
    -1.37
     does
    -1.34
     now
    -1.34
     if
    -1.25
     can
    -1.22
     should
    -1.16
     using
    -1.11
     has
    -1.09
    POSITIVE LOGITS
     وكان
    1.73
     وكانت
    1.53
     ήταν
    1.21
    ********/
    1.16
     homoto
    1.12
     më
    1.12
    began
    1.09
     approxim
    1.09
    **********/
    1.09
    CardView
    1.05
    Activations Density 0.038%

    No Known Activations