© 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. 26547
    Prev
    Next
    INDEX
    Explanations

    Greek descent or unregulated

    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
     It
    -1.44
     Because
    -1.39
     This
    -1.32
    because
    -1.16
    有不少
    -1.16
    řejmě
    -1.14
     different
    -1.13
     подготовка
    -1.13
     When
    -1.08
     when
    -1.07
    POSITIVE LOGITS
     juſ
    1.27
    𓁹
    1.25
    
    1.16
     efficacement
    1.13
     cacher
    1.13
     aujourd
    1.13
     花纹
    1.10
     siff
    1.09
     抠
    1.09
    ÍC
    1.09
    Activations Density 0.047%

    No Known Activations