© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 87281
    Prev
    Next
    INDEX
    Explanations

    error messages and warnings

    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
    {
    -2.03
    [
    -1.58
     what
    -1.49
     标
    -1.46
     to
    -1.37
     невели
    -1.36
    </b>
    -1.35
    </strong>
    -1.34
     notorious
    -1.34
     截图
    -1.34
    POSITIVE LOGITS
     diesem
    1.56
     consegui
    1.44
     telinga
    1.42
     of
    1.42
    が届
    1.41
     desembar
    1.41
     This
    1.40
    酪
    1.35
     着物
    1.35
    ровании
    1.34
    Activations Density 0.001%

    No Known Activations