© 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. 59031
    Prev
    Next
    INDEX
    Explanations

    data, LIABILITY, water, women

    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
     and
    -1.67
     by
    -1.48
    みたら
    -1.41
    :
    -1.24
     The
    -1.23
    section
    -1.14
     the
    -1.06
    THE
    -1.05
     teritor
    -1.05
     another
    -1.01
    POSITIVE LOGITS
     môžu
    1.48
     môže
    1.45
     Sélectionnez
    1.42
     proč
    1.41
     jednoduch
    1.37
     Ajoutez
    1.34
     větší
    1.34
     mesurer
    1.32
     Commencez
    1.31
    trường
    1.30
    Activations Density 0.086%

    No Known Activations