© 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. 100060
    Prev
    Next
    INDEX
    Explanations

    miss followed by nouns

    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
     einfachen
    -2.73
     sicheren
    -2.63
     vì
    -2.52
     täglichen
    -2.47
     Erfol
    -2.45
     möglichen
    -2.41
    uſe
    -2.34
     individuellen
    -2.27
     barring
    -2.27
     jeweiligen
    -2.27
    POSITIVE LOGITS
    ↵
    2.63
    什么的
    2.56
    ꜆
    2.55
    麪
    2.53
     که
    2.48
    ’，
    2.47
    𞤢
    2.45
    堿
    2.42
    骘
    2.41
    肫
    2.36
    Activations Density 0.017%

    No Known Activations