© 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. 90177
    Prev
    Next
    INDEX
    Explanations

    trying one's hand at

    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
    𝐚
    0.61
    𝙚
    0.54
    掄
    0.52
    ェ
    0.51
    olls
    0.50
    ikums
    0.49
    avn
    0.48
     tapes
    0.48
    ottle
    0.47
    afu
    0.47
    POSITIVE LOGITS
     кварти
    0.54
    ຕິດຕໍ່
    0.50
     нрави
    0.48
    Street
    0.46
    י
    0.46
    רים
    0.45
    Differences
    0.45
     સુધી
    0.44
     Mansion
    0.44
     noche
    0.44
    Activations Density 0.000%

    No Known Activations