© 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. 84234
    Prev
    Next
    INDEX
    Explanations

    know what or that

    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
     just
    -1.52
     simplemente
    -1.48
     simply
    -1.40
     odc
    -1.26
    beten
    -1.24
    ^{\
    -1.23
     national
    -1.21
    ’
    -1.20
     inkább
    -1.20
     nationale
    -1.20
    POSITIVE LOGITS
     that
    1.95
     of
    1.60
    了的
    1.41
     molta
    1.36
    ではでは
    1.29
    cembre
    1.29
    р
    1.29
     GONNA
    1.24
     from
    1.23
    このように
    1.23
    Activations Density 0.014%

    No Known Activations