© 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. 39270
    Prev
    Next
    INDEX
    Explanations

    possessive 's

    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
    えっ
    -1.48
    籏
    -1.47
    つづく
    -1.45
    きち
    -1.44
    あぁ
    -1.40
    に入れて
    -1.39
    おそ
    -1.39
    を変更
    -1.38
    ほら
    -1.31
    ほんと
    -1.30
    POSITIVE LOGITS
     as
    1.52
     before
    1.48
     when
    1.39
     is
    1.38
     while
    1.27
     it
    1.27
     ones
    1.25
     on
    1.23
     tropicales
    1.17
     offerings
    1.13
    Activations Density 0.028%

    No Known Activations