© 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-262K
    7. 1741
    Prev
    Next
    INDEX
    Explanations

    code structure and programming elements

    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_262k_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
    ➲
    0.32
    豕
    0.31
    ⚉
    0.29
    Flying
    0.28
    پا
    0.28
    悅
    0.28
    Lambda
    0.28
     ஆகிய
    0.28
    ей
    0.27
     prema
    0.27
    POSITIVE LOGITS
     recalls
    0.29
     ncols
    0.29
     vs
    0.29
    ``
    0.27
     estr
    0.27
     emph
    0.27
     covid
    0.27
     transcripts
    0.27
     instagram
    0.26
     testAvg
    0.26
    Activations Density 0.054%

    No Known Activations