© 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. 86531
    Prev
    Next
    INDEX
    Explanations

    job satisfaction, relationship satisfaction

    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
     but
    -1.62
    ("")]
    -1.45
    lesia
    -1.40
    鐧
    -1.39
     Wartawan
    -1.38
    xelles
    -1.36
    /}{
    -1.35
    momile
    -1.34
    ัติ
    -1.33
    unikasi
    -1.30
    POSITIVE LOGITS
     where
    1.59
     didn
    1.46
     at
    1.37
    ’
    1.32
     exatamente
    1.25
     have
    1.20
     wouldn
    1.18
    긍
    1.17
     doesn
    1.17
     gover
    1.16
    Activations Density 0.043%

    No Known Activations