© 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. 71218
    Prev
    Next
    INDEX
    Explanations

    UI elements and containers

    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
     its
    -1.65
     évé
    -1.47
    贋
    -1.44
    /");
    -1.41
     (
    -1.34
     bolsos
    -1.32
     adornos
    -1.31
     cadeaux
    -1.30
    wered
    -1.30
     intér
    -1.29
    POSITIVE LOGITS
     ailing
    1.51
     nedeniyle
    1.48
    Hilsen
    1.41
     contextLoads
    1.39
    了几
    1.29
    了一個
    1.23
     posh
    1.22
    P
    1.20
    M
    1.20
     frigid
    1.17
    Activations Density 0.001%

    No Known Activations