© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 44076
    Prev
    Next
    INDEX
    Explanations

    is a / was a

    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
     навіть
    -1.44
    甚至
    -1.27
     โดย
    -1.23
     ویکی‌پدیا
    -1.22
     thậm
    -1.22
    échange
    -1.21
    ==""){
    -1.19
     ہے۔
    -1.18
     slår
    -1.18
    çou
    -1.16
    POSITIVE LOGITS
     to
    1.87
     now
    1.64
     for
    1.60
     and
    1.55
     since
    1.49
     if
    1.45
    openhague
    1.38
     themselves
    1.33
     when
    1.30
     because
    1.29
    Activations Density 0.064%

    No Known Activations