© 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. 169640
    Prev
    Next
    INDEX
    Explanations

    a way to talk about examples

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

    content creation and argumentation

    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
    дачи
    0.48
    ​
    0.47
    Kis
    0.43
    ด้
    0.43
     Mpc
    0.42
    =="
    0.41
    Xem
    0.41
    ​​​​
    0.41
    挤
    0.40
    เสีย
    0.40
    POSITIVE LOGITS
     infuse
    0.52
     의견
    0.50
    eful
    0.49
     infusions
    0.49
     opiniones
    0.47
     intravenously
    0.47
     Necklace
    0.46
     illo
    0.46
     vooraf
    0.45
     ऑर्गे
    0.45
    Activations Density 0.000%

    No Known Activations