© 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. 15182
    Prev
    Next
    INDEX
    Explanations

    b followed by numbers or symbols

    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
     one
    -1.54
     two
    -1.37
     other
    -1.35
     enhancing
    -1.30
     your
    -1.22
        
    -1.20
    in
    -1.19
     adding
    -1.18
    to
    -1.11
    ν
    -1.11
    POSITIVE LOGITS
    EMPO
    1.39
     ใน
    1.32
    mbgg
    1.27
     zarówno
    1.27
     occupé
    1.26
    糜
    1.25
     presque
    1.23
     jedynie
    1.23
    峮
    1.20
    Ⴀ
    1.20
    Activations Density 0.226%

    No Known Activations