© 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. 14251
    Prev
    Next
    INDEX
    Explanations

    getting data from

    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
     latter
    -1.35
    -1.34
     lmao
    -1.29
    ਲ਼
    -1.25
     серебри
    -1.25
     exceptional
    -1.23
    didn
    -1.22
     neumáticos
    -1.21
     qua
    -1.20
    soon
    -1.20
    POSITIVE LOGITS
     fourteen
    1.13
    しているので
    1.12
     manchmal
    1.12
    딪
    1.11
     eleven
    1.11
     sixteen
    1.06
     thirteen
    1.06
     fifteen
    1.06
     Hust
    1.05
    他にも
    1.03
    Activations Density 0.348%

    No Known Activations