© 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. 31-GEMMASCOPE-2-RES-65K
    7. 61449
    Prev
    Next
    INDEX
    Explanations

    sky is blue

    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
    (")
    0.46
    발
    0.43
    (";
    0.43
    vs
    0.42
    ഷ്‌
    0.41
    ovsk
    0.41
    ("\
    0.41
    libat
    0.41
    呷
    0.41
    (",
    0.41
    POSITIVE LOGITS
     structure
    0.48
     conexion
    0.48
     negocio
    0.47
     store
    0.47
     moneda
    0.46
    ά
    0.46
     শ্রেণীর
    0.45
     sticker
    0.45
     όπως
    0.45
     plays
    0.45
    Activations Density 0.001%

    No Known Activations