© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 70045
    Prev
    Next
    INDEX
    Explanations

    dragon boat festival

    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
     you
    -1.54
     your
    -1.32
    ⅕
    -1.20
     этих
    -1.15
    ujące
    -1.14
     accél
    -1.10
    ⅔
    -1.10
    циях
    -1.09
    を超
    -1.09
    淡淡的
    -1.09
    POSITIVE LOGITS
     each
    1.85
     they
    1.61
    They
    1.53
     partecip
    1.27
     themselves
    1.23
     teritor
    1.20
    鱟
    1.19
    鏵
    1.17
     every
    1.17
     chaque
    1.16
    Activations Density 0.074%

    No Known Activations