© 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. 247794
    Prev
    Next
    INDEX
    Explanations

    books and pages

    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
    毕
    0.52
    ákat
    0.50
    ớp
    0.49
    baka
    0.49
    alne
    0.49
    xlink
    0.48
    első
    0.48
    rägen
    0.48
    𝐝
    0.48
    nagy
    0.48
    POSITIVE LOGITS
     известно
    0.48
     Yellowstone
    0.48
     программы
    0.48
     chromosomes
    0.47
     logs
    0.47
     informa
    0.47
    どれ
    0.47
     tesam
    0.46
     約
    0.46
     obliter
    0.46
    Activations Density 0.000%

    No Known Activations