© 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-16K
    7. 8939
    Prev
    Next
    INDEX
    Explanations

    percentages and numerical increases

    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_16k_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
     점점
    0.41
     বান
    0.38
     sparingly
    0.37
     слегка
    0.37
     немно
    0.37
    녜
    0.37
    间的
    0.37
     высокая
    0.36
     batería
    0.36
     સહ
    0.35
    POSITIVE LOGITS
    %
    0.64
     (+
    0.63
     yüzde
    0.62
     %
    0.62
     सुमारे
    0.59
    %。
    0.59
     শতকরা
    0.59
    %-
    0.58
    \%
    0.57
     சுமார்
    0.56
    Activations Density 0.173%

    No Known Activations