© 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. 66306
    Prev
    Next
    INDEX
    Explanations

    largest, leading, or foremost

    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
     melang
    -1.43
    媖
    -1.41
     that
    -1.35
    棪
    -1.34
     Pekan
    -1.33
    ________,
    -1.30
     gerak
    -1.30
    卨
    -1.30
    塒
    -1.27
    keted
    -1.27
    POSITIVE LOGITS
    "
    1.48
     VERY
    1.38
     foremost
    1.35
     فقط
    1.33
     premier
    1.30
     distinctive
    1.27
    只有
    1.27
     exceedingly
    1.26
     csak
    1.25
     REALLY
    1.24
    Activations Density 0.027%

    No Known Activations