© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 105318
    Prev
    Next
    INDEX
    Explanations

    static keyword declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    اخ
    0.68
    s
    0.61
    um
    0.57
    ab
    0.54
     लैंग
    0.53
     Thái
    0.53
    abt
    0.52
    ération
    0.52
    嫋
    0.52
    oti
    0.50
    POSITIVE LOGITS
     ומ
    0.59
     aument
    0.58
    테
    0.56
     Args
    0.55
    B
    0.55
     lobbies
    0.54
     argu
    0.54
    하며
    0.54
    jski
    0.54
    :"
    0.54
    Activations Density 0.000%

    No Known Activations