© 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. 35201
    Prev
    Next
    INDEX
    Explanations

    specifying conditions or alternatives

    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
    叽
    -1.09
     שונים
    -1.06
     différents
    -1.02
     QUÉ
    -1.02
     restent
    -1.01
    nellement
    -0.95
     distintos
    -0.95
    色々な
    -0.93
     ۱۵
    -0.91
    .《
    -0.91
    POSITIVE LOGITS
     or
    1.66
     other
    1.59
     any
    1.46
     хотя
    1.23
     significant
    1.16
     других
    1.16
    ircraft
    1.14
     другими
    1.09
     ANY
    1.06
     have
    1.05
    Activations Density 0.045%

    No Known Activations