© 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. 16-GEMMASCOPE-2-RES-262K
    7. 88823
    Prev
    Next
    INDEX
    Explanations

    asterisk and space patterns

    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_16_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
     avrà
    0.58
     auront
    0.52
    =
    0.51
     onge
    0.51
     effectuées
    0.50
    ા
    0.50
     réalisées
    0.50
     ripping
    0.49
     warping
    0.49
    лежа
    0.48
    POSITIVE LOGITS
     חד
    0.63
    मि
    0.53
    ỗi
    0.52
    न्दे
    0.51
    㫜
    0.51
    tois
    0.50
     fertilized
    0.49
    shy
    0.49
    त्र
    0.49
    υτό
    0.49
    Activations Density 0.002%

    No Known Activations