© 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. 7248
    Prev
    Next
    INDEX
    Explanations

    service charges

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

    potential, engine, fantasy, pineapple

    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
     Odyssey
    0.49
    side
    0.46
     Blvd
    0.45
    -
    0.45
    ->
    0.42
     Vis
    0.42
     fle
    0.42
     unbe
    0.42
     algorit
    0.41
     shore
    0.41
    POSITIVE LOGITS
     الأكثر
    0.57
    l
    0.55
     gră
    0.50
    OLYBD
    0.50
    Benzoimidazol
    0.49
    opération
    0.48
    TabBar
    0.48
     тър
    0.48
    kjhtml
    0.47
     மாணவர்கள்
    0.47
    Activations Density 0.001%

    No Known Activations