© 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. 209583
    Prev
    Next
    INDEX
    Explanations

    Chinese, resistant, oil, advocate

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

    specifying terms and descriptions

    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
    podcast
    0.45
    ల
    0.43
     Podcast
    0.42
     prioritizing
    0.41
     webcam
    0.40
    idazol
    0.40
    lá
    0.40
     finalizing
    0.40
    mack
    0.40
    सरत
    0.40
    POSITIVE LOGITS
    新增
    0.54
    ın
    0.49
    的
    0.47
     COMMERCIAL
    0.47
     其实
    0.47
     AVAILABLE
    0.46
     REQUIREMENTS
    0.46
     因为
    0.46
     DEPEND
    0.46
     Shig
    0.46
    Activations Density 0.000%

    No Known Activations