© 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. 35053
    Prev
    Next
    INDEX
    Explanations

    Power Tools

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

    for a or an

    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
    奢
    0.56
    ᑖ
    0.53
    淪
    0.52
     катастро
    0.51
    浪费
    0.50
    蹉
    0.49
    摭
    0.48
    រយៈ
    0.48
    墙
    0.48
    葶
    0.48
    POSITIVE LOGITS
     software
    0.57
     flexible
    0.55
     new
    0.50
    .
    0.50
     flavored
    0.49
     growth
    0.48
     connector
    0.48
     pancake
    0.47
    nostic
    0.47
     connecting
    0.47
    Activations Density 0.000%

    No Known Activations