© 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. 88924
    Prev
    Next
    INDEX
    Explanations

    removing redundancy

    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
    (
    1.13
    ق
    0.98
    li
    0.94
    对
    0.92
    ف
    0.84
    in
    0.82
    大
    0.81
    en
    0.79
    ch
    0.79
    of
    0.79
    POSITIVE LOGITS
     redundancy
    0.86
    ור
    0.86
    redund
    0.85
    ί
    0.85
    ну
    0.80
     redundant
    0.79
     común
    0.78
    ी
    0.76
     tých
    0.72
     harus
    0.71
    Activations Density 0.008%

    No Known Activations