© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 47413
    Prev
    Next
    INDEX
    Explanations

    setting up instructions

    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_31_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
    ដ៏
    0.49
    ideos
    0.48
     industriales
    0.48
    𝐡
    0.47
    कला
    0.47
     científ
    0.46
    tFileInputExcel
    0.45
     estrogens
    0.44
     отрасли
    0.44
    Furn
    0.43
    POSITIVE LOGITS
     prior
    0.47
     in
    0.46
    にした
    0.46
     kita
    0.45
     generic
    0.44
     Shyam
    0.44
     प्रतिबंध
    0.43
    ↵↵
    0.43
    の設定
    0.41
     cookie
    0.41
    Activations Density 0.002%

    No Known Activations