© 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. 12493
    Prev
    Next
    INDEX
    Explanations

    sentence start detection

    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
     néanmoins
    -1.29
    rawn
    -1.24
     then
    -1.21
     अन्य
    -1.20
    osphere
    -1.18
    ………………
    -1.16
     Dinas
    -1.15
    yyyyy
    -1.14
     but
    -1.13
     altres
    -1.12
    POSITIVE LOGITS
     too
    1.43
     in
    1.41
     which
    1.39
    Although
    1.36
    Again
    1.34
     as
    1.34
     such
    1.32
     like
    1.32
     again
    1.27
     by
    1.25
    Activations Density 0.013%

    No Known Activations