© 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-65K
    7. 2636
    Prev
    Next
    INDEX
    Explanations

    code and lists

    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_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
     I
    0.48
    ों
    0.43
    ۰
    0.41
    لی
    0.38
    ς
    0.36
    ের
    0.36
    ری
    0.36
    on
    0.36
    bs
    0.35
    cdot
    0.35
    POSITIVE LOGITS
     Fortsch
    0.43
    是将
    0.42
     كيف
    0.42
     ingresar
    0.42
     chandelier
    0.42
     beispielsweise
    0.42
     forged
    0.41
     свето
    0.41
     argomento
    0.41
     pojawi
    0.41
    Activations Density 3.211%

    No Known Activations