© 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. 71293
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb

    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
     in
    -1.61
    इटम
    -1.48
     then
    -1.43
    </h4>
    -1.38
    ătate
    -1.34
     estaban
    -1.32
    pēc
    -1.30
    辔
    -1.30
    ссию
    -1.30
    อื่น
    -1.28
    POSITIVE LOGITS
    6
    2.27
    0
    2.19
    7
    2.14
    5
    2.11
    9
    1.94
    8
    1.75
    3
    1.67
    k
    1.66
    .
    1.64
    光是
    1.49
    Activations Density 0.061%

    No Known Activations