© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3933
    Prev
    Next
    INDEX
    Explanations

    formatting markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
     historians
    2.19
    囝
    1.87
    зидента
    1.85
    にか
    1.77
     historian
    1.69
     biographer
    1.68
     ihe
    1.62
    рин
    1.62
     favourites
    1.62
    뎐
    1.62
    POSITIVE LOGITS
    quetas
    2.79
    说完
    2.60
    ogany
    2.21
    Таким
    2.19
    지막
    2.17
    owels
    2.15
    ючи
    2.13
     Таким
    2.13
    7
    2.13
    req
    2.12
    Activations Density 0.422%

    No Known Activations