© 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. 10-GEMMASCOPE-RES-131K
    7. 14939
    Prev
    Next
    INDEX
    Explanations

    World, borne, ops, Eyed, Giants, legendary

    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_10/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
     zarówno
    -1.42
    𞤢
    -1.39
    仕方ない
    -1.33
     zuhause
    -1.33
     Каждый
    -1.32
    だけでなく
    -1.31
    抠
    -1.29
    坨
    -1.27
    これらの
    -1.27
    灩
    -1.27
    POSITIVE LOGITS
     miliardi
    1.34
     improve
    1.25
    ak
    1.24
     caos
    1.23
    rightarrow
    1.21
     Calls
    1.13
    根据
    1.12
     harus
    1.12
     correct
    1.11
    Eine
    1.09
    Activations Density 0.003%

    No Known Activations