© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75296
    Prev
    Next
    INDEX
    Explanations

    line color or pattern

    np_acts-logits-general · gemini-2.5-flash-lite

    stroke and brush drawing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     কাজটি
    0.42
    বিবি
    0.40
     pertanian
    0.39
     높아
    0.39
    鶚
    0.39
     adım
    0.39
    텔
    0.38
     Listening
    0.38
     Kayla
    0.38
    郏
    0.38
    POSITIVE LOGITS
    circ
    0.47
    錦
    0.45
     ThemeOverlay
    0.44
     stroke
    0.43
    锦
    0.42
     lineColor
    0.40
     wallpaper
    0.40
     Stroke
    0.40
     circ
    0.39
     disc
    0.39
    Activations Density 0.003%

    No Known Activations