© 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. 26892
    Prev
    Next
    INDEX
    Explanations

    coordinate positions and dimensions

    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
     nový
    -1.20
    になれる
    -1.17
    のお知らせ
    -1.17
     ktorá
    -1.16
     utilizan
    -1.16
     samoch
    -1.14
     Einblick
    -1.14
    をお願い
    -1.13
    ⅽ
    -1.13
    UIManager
    -1.12
    POSITIVE LOGITS
    そして
    1.09
     antik
    1.02
     veren
    0.97
     hant
    0.97
    是一款
    0.96
     fantasma
    0.95
     Luar
    0.95
     Karena
    0.94
     beri
    0.94
    を
    0.92
    Activations Density 0.005%

    No Known Activations