© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 39876
    Prev
    Next
    INDEX
    Explanations

    every now and again

    np_acts-logits-general · gemini-2.5-flash-lite

    human qualities and community actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    o
    0.48
    ly
    0.48
     helped
    0.48
     facilitated
    0.48
     New
    0.47
     altre
    0.46
     opposed
    0.46
     less
    0.46
    e
    0.46
     largely
    0.46
    POSITIVE LOGITS
     человек
    0.55
    这些人
    0.54
     člove
    0.52
    有一种
    0.49
     člov
    0.48
     человека
    0.47
     человеку
    0.47
     челове
    0.46
     индиви
    0.46
    勇敢
    0.46
    Activations Density 0.000%

    No Known Activations