© 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. 22-GEMMASCOPE-RES-131K
    7. 128309
    Prev
    Next
    INDEX
    Explanations

    dates and occurrences

    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_22/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
     tuta
    -1.26
     inconvénients
    -1.25
     mahu
    -1.21
     consectetur
    -1.20
     kui
    -1.19
     berge
    -1.12
     Deber
    -1.12
     veľa
    -1.12
     cérami
    -1.12
     kuv
    -1.12
    POSITIVE LOGITS
     new
    1.41
     and
    1.41
     these
    1.24
     news
    1.22
     health
    1.13
     woman
    1.13
     them
    1.13
     eficaz
    1.12
     questions
    1.12
     they
    1.11
    Activations Density 0.002%

    No Known Activations