© 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. 9144
    Prev
    Next
    INDEX
    Explanations

    right-click or right

    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
     brasil
    0.37
    fool
    0.37
     Quarter
    0.37
    flutter
    0.36
     poly
    0.36
    阃
    0.35
     Bottom
    0.35
     Flutter
    0.35
     Sandbox
    0.35
     flutter
    0.34
    POSITIVE LOGITS
     right
    1.40
    Right
    1.29
     Right
    1.29
    right
    1.20
     RIGHT
    1.14
    右
    1.08
     право
    1.00
    RIGHT
    0.98
     右
    0.98
     droit
    0.90
    Activations Density 0.093%

    No Known Activations