© 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. 85509
    Prev
    Next
    INDEX
    Explanations

    ranking, listing, grating, craving, longing, offering

    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
     atau
    -3.02
     cinese
    -2.89
    是
    -2.86
     یا
    -2.69
    风
    -2.67
    “
    -2.63
     lancia
    -2.59
    ﮏ
    -2.45
     etek
    -2.39
    𝑚
    -2.34
    POSITIVE LOGITS
     causando
    3.11
     creando
    2.98
     generando
    2.73
     of
    2.70
     bekannten
    2.66
     umfang
    2.59
     procurando
    2.58
    姈
    2.58
     tornando
    2.50
     its
    2.48
    Activations Density 0.059%

    No Known Activations