© 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. 71279
    Prev
    Next
    INDEX
    Explanations

    acted upon by agency

    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
    はずです
    -1.29
    気がします
    -1.29
    臯
    -1.26
     geralmente
    -1.16
    と話
    -1.11
     require
    -1.08
    んでる
    -1.05
    なた
    -1.05
     hjälper
    -1.05
    都會
    -1.04
    POSITIVE LOGITS
     by
    3.36
     from
    2.02
     oleh
    1.63
     with
    1.57
     توسط
    1.49
     bởi
    1.44
     tarafından
    1.36
    ATIVES
    1.34
    は
    1.20
    mán
    1.19
    Activations Density 0.084%

    No Known Activations