© 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. 217068
    Prev
    Next
    INDEX
    Explanations

    special ballet

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

    officially became

    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
    ="../
    0.45
    ホ
    0.45
    帆
    0.44
    itoneal
    0.43
    )?
    0.43
    ?
    0.43
    Вт
    0.42
    谐
    0.42
    ﻫ
    0.41
    犬
    0.41
    POSITIVE LOGITS
    णासाठी
    0.57
     vitória
    0.53
     jumlah
    0.50
     Đi
    0.49
     siguió
    0.49
     zatím
    0.49
     Jika
    0.49
     Quando
    0.48
     що
    0.48
     primeira
    0.48
    Activations Density 0.001%

    No Known Activations