© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13757
    Prev
    Next
    INDEX
    Explanations

    expresses an opinion or feeling

    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
    ~~~~~
    -1.86
     दोनों
    -1.84
     dozens
    -1.74
    íte
    -1.65
    我们
    -1.65
    ası
    -1.61
    🎉
    -1.61
    rvats
    -1.58
    ~~~~~~
    -1.56
    寶
    -1.56
    POSITIVE LOGITS
     \
    2.03
    ໊
    1.71
    脚下
    1.66
    赑
    1.59
     you
    1.59
     befes
    1.59
     if
    1.59
     THROUGH
    1.59
    袪
    1.58
     ‚
    1.56
    Activations Density 0.013%

    No Known Activations