© 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. 116474
    Prev
    Next
    INDEX
    Explanations

    look for

    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
    le
    0.69
     havde
    0.69
    ل
    0.65
    ı
    0.64
    ką
    0.61
    lə
    0.61
     altid
    0.61
    İ
    0.61
    ő
    0.59
    尔
    0.59
    POSITIVE LOGITS
    versive
    0.55
     festive
    0.54
    회가
    0.54
    وراق
    0.54
     monstros
    0.54
     galvanized
    0.52
    (
    0.52
     lucrative
    0.52
    ずれ
    0.51
     حتی
    0.51
    Activations Density 0.012%

    No Known Activations