© 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. 31-GEMMASCOPE-2-RES-262K
    7. 126974
    Prev
    Next
    INDEX
    Explanations

    sweeping and brushing

    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_31_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
    ulk
    0.50
    shah
    0.49
     atyp
    0.48
    ல்
    0.47
    咙
    0.46
     sham
    0.46
    টর
    0.46
    diamond
    0.45
    aus
    0.45
    sham
    0.45
    POSITIVE LOGITS
     swept
    1.13
     sweep
    1.09
     sweeping
    1.08
     sweeps
    1.04
     Sweep
    0.96
    Sweep
    0.90
    扫
    0.86
     brushing
    0.80
    掃
    0.79
     brushes
    0.76
    Activations Density 0.033%

    No Known Activations