© 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. 81092
    Prev
    Next
    INDEX
    Explanations

    special characters

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

    special characters and multilingual content

    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
     M
    0.54
     Nella
    0.52
     Aix
    0.52
     D
    0.52
     Q
    0.52
     G
    0.50
     Μ
    0.50
     H
    0.50
     U
    0.49
     SFR
    0.49
    POSITIVE LOGITS
    됐
    0.48
    い
    0.47
    磁盘
    0.47
    但这
    0.47
    科研
    0.46
    يك
    0.45
    行李
    0.45
    业
    0.45
    ATIC
    0.45
     ఎంత
    0.45
    Activations Density 0.001%

    No Known Activations