© 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. 128328
    Prev
    Next
    INDEX
    Explanations

    fines, sentences, and monetary amounts

    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
     our
    -1.44
     we
    -1.36
     these
    -1.09
    itaji
    -1.09
     наших
    -1.03
     coloré
    -1.03
     måske
    -1.03
     \{
    -1.02
    sometimes
    -1.02
    viève
    -1.02
    POSITIVE LOGITS
     three
    1.46
    ditionally
    1.43
     will
    1.41
     лечения
    1.37
     two
    1.35
     five
    1.23
     medical
    1.20
    経過
    1.17
    两
    1.14
    three
    1.13
    Activations Density 0.015%

    No Known Activations