© 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. 117016
    Prev
    Next
    INDEX
    Explanations

    sub sandwich

    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
    ir
    0.57
    al
    0.54
    ні
    0.52
    g
    0.52
    branded
    0.51
    uah
    0.51
    f
    0.50
    re
    0.50
    trans
    0.50
    well
    0.50
    POSITIVE LOGITS
     rodeo
    0.65
     arsenal
    0.61
     ducks
    0.60
     orchestras
    0.58
     cowboys
    0.57
     (
    0.56
     salto
    0.56
     passada
    0.55
     concerto
    0.54
     cows
    0.54
    Activations Density 0.000%

    No Known Activations