© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128246
    Prev
    Next
    INDEX
    Explanations

    this. members, SET property

    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
    lında
    -1.33
    ,‎
    -1.18
    ᶜ
    -1.09
    åter
    -1.07
     sorprender
    -1.05
    vatten
    -1.05
     させ
    -1.05
     nimi
    -1.05
    olesome
    -1.04
     тях
    -1.04
    POSITIVE LOGITS
     even
    0.93
     we
    0.90
     time
    0.88
     one
    0.88
     February
    0.85
     faster
    0.85
     by
    0.85
    اعده
    0.85
     skechers
    0.84
     torino
    0.84
    Activations Density 0.003%

    No Known Activations