© 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. 40-GEMMASCOPE-2-RES-65K
    7. 53333
    Prev
    Next
    INDEX
    Explanations

    Tikz, LaTeX, Postscript, code generation

    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_40_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
     جن
    0.41
     পয়
    0.41
    সান
    0.39
    ণু
    0.39
    ISPW
    0.39
    ত্ত্ব
    0.38
    聪
    0.38
     समु
    0.38
    サン
    0.38
    蹶
    0.38
    POSITIVE LOGITS
    liers
    0.42
     white
    0.41
    anted
    0.41
    cloudinary
    0.40
    anned
    0.40
     White
    0.38
     whitew
    0.38
    白
    0.38
    antic
    0.38
    ann
    0.37
    Activations Density 0.004%

    No Known Activations