© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 50264
    Prev
    Next
    INDEX
    Explanations

    as Outstanding, an, shown

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

    explanations of complex topics

    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
    rically
    0.50
     rato
    0.44
    \}^{
    0.42
     sketchy
    0.41
    嘖
    0.40
     ዓይነት
    0.39
    zem
    0.39
     colourful
    0.38
     sweeter
    0.38
    emplate
    0.38
    POSITIVE LOGITS
     obstacle
    0.48
     א
    0.47
     छापे
    0.45
     ノ
    0.44
     مک
    0.43
    苍
    0.43
     スク
    0.43
     ノー
    0.42
    これを
    0.42
     カ
    0.42
    Activations Density 0.000%

    No Known Activations