© 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. 34-GEMMASCOPE-RES-131K
    7. 78830
    Prev
    Next
    INDEX
    Explanations

    actions of speaking

    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_34/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
     hesitation
    -1.09
     is
    -0.93
     отредакти
    -0.93
     pengaruh
    -0.93
     Touristen
    -0.90
     courtesy
    -0.89
     lekko
    -0.87
    руп
    -0.85
     satisfactory
    -0.84
     نوشته
    -0.84
    POSITIVE LOGITS
     calling
    1.54
     saying
    1.37
     asking
    1.25
     demanding
    1.24
     exclaim
    1.23
    calling
    1.20
     fling
    1.19
     constantly
    1.19
     telling
    1.14
    Calling
    1.11
    Activations Density 0.052%

    No Known Activations