© 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. 40-GEMMASCOPE-2-RES-262K
    7. 131676
    Prev
    Next
    INDEX
    Explanations

    brush, brushes, paintbrush

    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_40_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
     piernas
    0.42
    IllegalArgument
    0.42
    ौरा
    0.41
     मीटर
    0.40
     गैंग
    0.39
     sledge
    0.39
    ソール
    0.38
    庥
    0.38
    autical
    0.36
     parliamentary
    0.36
    POSITIVE LOGITS
     brush
    1.43
     brushes
    1.41
     Brush
    1.28
     paintbrush
    1.18
    brush
    1.17
    Brush
    1.17
     brushing
    1.10
    brushes
    1.09
     ब्रश
    1.08
     brushed
    1.03
    Activations Density 0.011%

    No Known Activations