© 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. 22257
    Prev
    Next
    INDEX
    Explanations

    software versions or version numbers

    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
     mengerti
    -1.52
    这不是
    -1.45
     Поэтому
    -1.45
     indescri
    -1.44
     EXCELL
    -1.41
     Therefore
    -1.41
    不得不说
    -1.40
    他知道
    -1.39
    キャベツ
    -1.39
    好久
    -1.39
    POSITIVE LOGITS
     bambú
    1.41
     version
    1.41
    луйста
    1.38
     burbujas
    1.35
     adecuada
    1.34
    rhosis
    1.30
     ótima
    1.30
     your
    1.30
    ınızı
    1.30
    ↵↵
    1.27
    Activations Density 0.062%

    No Known Activations