© 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. 105024
    Prev
    Next
    INDEX
    Explanations

    Streamlit sidebar code

    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
    ia
    0.70
    ge
    0.67
    se
    0.66
    ör
    0.66
    ly
    0.66
     U
    0.64
    ian
    0.64
     Harper
    0.64
    鲸
    0.64
    gg
    0.63
    POSITIVE LOGITS
     élections
    0.75
     ngươi
    0.71
    ку
    0.69
    на
    0.68
    の時間
    0.68
    وں
    0.68
    رک
    0.68
    ap
    0.67
    ای
    0.67
    sidebar
    0.67
    Activations Density 0.001%

    No Known Activations