© 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. 41-GEMMASCOPE-2-RES-262K
    7. 58372
    Prev
    Next
    INDEX
    Explanations

    flip, resell, flipped, flipping

    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_all/layer_41_width_262k_l0_big
    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
     transactions
    0.44
     transaction
    0.43
     cour
    0.42
     transacción
    0.42
    繳
    0.42
    取引
    0.41
     cesse
    0.41
     acced
    0.41
    ികളുടെ
    0.40
    ธุรก
    0.39
    POSITIVE LOGITS
     flip
    0.81
     resell
    0.77
     flipped
    0.77
     flipping
    0.75
    flip
    0.75
     Flip
    0.72
    Flip
    0.70
    flipped
    0.69
     resale
    0.68
    翻
    0.68
    Activations Density 0.001%

    No Known Activations