© 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. 26847
    Prev
    Next
    INDEX
    Explanations

    `Nebraska Supreme`, `Studywise`, `Coal,`, `How Much`

    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
     you
    -1.30
     when
    -1.20
     ketika
    -1.12
    lepiej
    -1.09
     cueva
    -1.08
     Spisak
    -1.06
     three
    -1.05
     יְ
    -1.03
    クシー
    -1.03
     razu
    -1.02
    POSITIVE LOGITS
    especially
    1.07
     これ
    1.05
    particularly
    1.04
     パウダー
    1.03
    チ
    1.00
     особенно
    1.00
    iritual
    1.00
    妯
    0.97
    肛
    0.97
    特别是
    0.96
    Activations Density 0.000%

    No Known Activations