© 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. 67600
    Prev
    Next
    INDEX
    Explanations

    expressions of happiness

    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
     fragte
    -1.58
     not
    -1.51
    '
    -1.50
    The
    -1.46
     erinner
    -1.45
     The
    -1.37
    するので
    -1.35
    ፥
    -1.35
     mussten
    -1.34
    を使用
    -1.31
    POSITIVE LOGITS
     Joaqu
    1.38
    这让
    1.36
    +++++
    1.36
     Germania
    1.33
     techo
    1.31
     crisi
    1.27
     senha
    1.26
    鬭
    1.26
    usd
    1.26
    ceptable
    1.24
    Activations Density 0.010%

    No Known Activations