© 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. 27363
    Prev
    Next
    INDEX
    Explanations

    names and places

    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
    時々
    -1.51
    凄く
    -1.27
    ほんとに
    -1.20
    うまい
    -1.20
     continually
    -1.20
    色々と
    -1.19
    こいつ
    -1.17
     begeistert
    -1.17
    絶対に
    -1.16
     gewährle
    -1.16
    POSITIVE LOGITS
     There
    1.38
     there
    1.36
     if
    1.34
    Tienen
    1.33
     who
    1.25
     别墅
    1.23
     jambe
    1.20
     in
    1.13
     still
    1.12
     family
    1.11
    Activations Density 0.041%

    No Known Activations