© 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. 66259
    Prev
    Next
    INDEX
    Explanations

    code snippets and document structures

    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
     confortável
    -1.32
     serdecznie
    -1.29
     Spanyol
    -1.27
     Kullan
    -1.24
     unicórnio
    -1.24
     flexível
    -1.23
     TÉ
    -1.23
     feminino
    -1.21
     your
    -1.20
     reduz
    -1.18
    POSITIVE LOGITS
    1.29
    u
    1.14
    w
    1.13
    pro
    1.07
     just
    1.05
    rr
    1.05
    m
    1.05
    2
    1.05
    www
    1.03
    h
    1.03
    Activations Density 0.001%

    No Known Activations