© 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. 13633
    Prev
    Next
    INDEX
    Explanations

    questions and comparisons

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

    questions and explanations

    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
     ибо
    0.55
    崭
    0.52
    Hiện
    0.51
    𝗙
    0.51
    년간
    0.49
    ďaka
    0.49
    ງ
    0.49
    Así
    0.48
    ústria
    0.48
    诸多
    0.48
    POSITIVE LOGITS
     viewing
    0.55
    ？
    0.55
     limitations
    0.53
    ?
    0.52
     concerning
    0.50
     information
    0.50
     relationship
    0.50
     paragraph
    0.50
     indicate
    0.50
     basketball
    0.49
    Activations Density 0.015%

    No Known Activations