© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129809
    Prev
    Next
    INDEX
    Explanations

    section or chapter

    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
    _
    -1.20
    嬸
    -1.03
    by
    -1.02
    ฐ
    -1.01
    There
    -0.99
    ènements
    -0.96
    Because
    -0.96
    dă
    -0.96
    嚕
    -0.95
    醯
    -0.94
    POSITIVE LOGITS
     всички
    1.20
    Istorija
    1.16
     могат
    1.14
     dục
    1.13
     Cualquier
    1.10
     chapter
    1.10
     hlavně
    1.07
     дори
    1.06
     then
    1.04
     chapters
    1.03
    Activations Density 0.010%

    No Known Activations