© 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. 70631
    Prev
    Next
    INDEX
    Explanations

    physical postures

    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
     this
    -1.94
     by
    -1.52
     of
    -1.52
     on
    -1.41
     will
    -1.39
     there
    -1.38
    〜。
    -1.34
     with
    -1.30
     at
    -1.30
     a
    -1.27
    POSITIVE LOGITS
     getragen
    1.43
     takich
    1.38
     coûts
    1.35
    ところに
    1.34
     catégories
    1.29
    veranstaltungen
    1.28
     fraî
    1.27
    angebote
    1.24
    色んな
    1.23
    櫺
    1.23
    Activations Density 0.000%

    No Known Activations