© 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. 44535
    Prev
    Next
    INDEX
    Explanations

    feelings and states

    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
    Кто
    -1.68
    他们
    -1.52
    我们
    -1.38
     Either
    -1.35
    Что
    -1.34
    เรา
    -1.33
    เริ่ม
    -1.33
     they
    -1.31
     Kenntnis
    -1.30
    سبة
    -1.29
    POSITIVE LOGITS
     of
    1.55
     which
    1.55
    ’
    1.49
     and
    1.47
     with
    1.38
    ">“
    1.38
    ⁛
    1.36
    割と
    1.34
     possibility
    1.31
     ۱۵
    1.27
    Activations Density 0.010%

    No Known Activations