© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 138592
    Prev
    Next
    INDEX
    Explanations

    who are

    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
    ↵
    1.07
    h
    0.97
    on
    0.90
    '
    0.90
    尔
    0.75
    ገልግሎ
    0.75
    u
    0.74
    ক্স
    0.72
    hwar
    0.72
    ið
    0.72
    POSITIVE LOGITS
     who
    0.99
     quien
    0.81
    ,]
    0.79
    0.75
     by
    0.73
    ?)
    0.72
    馋
    0.71
    <unused2133>
    0.71
     दूसरों
    0.70
    ]\
    0.68
    Activations Density 0.010%

    No Known Activations