© 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. 52103
    Prev
    Next
    INDEX
    Explanations

    difference or recipe descriptions

    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
     الجم
    0.50
    ގ
    0.48
    ချ
    0.47
     ಸಂಧಿ
    0.44
     ಅನೇಕ
    0.43
     жив
    0.43
     استح
    0.43
     ರಚ
    0.43
    溧
    0.43
     сило
    0.42
    POSITIVE LOGITS
     abierto
    0.51
    of
    0.49
    ores
    0.48
     mismo
    0.48
    idden
    0.47
    ě
    0.45
     administrat
    0.45
    int
    0.44
    iciado
    0.44
    Hace
    0.43
    Activations Density 0.002%

    No Known Activations