© 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. 39657
    Prev
    Next
    INDEX
    Explanations

    Clement names

    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
    锨
    -2.73
    of
    -2.64
     решения
    -2.59
     They
    -2.56
     momentan
    -2.47
     möglichen
    -2.38
     overriding
    -2.36
     wist
    -2.34
     причин
    -2.34
     gesuchten
    -2.30
    POSITIVE LOGITS
    赑
    2.95
    汌
    2.58
     мои
    2.41
    それから
    2.23
    聼
    2.23
     grego
    2.22
    尛
    2.19
    这件事
    2.19
    ꯵
    2.17
    橚
    2.14
    Activations Density 0.001%

    No Known Activations