© 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. 11674
    Prev
    Next
    INDEX
    Explanations

    radish, radical, radiate

    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
     Goodbye
    0.41
    ܐ
    0.39
    지
    0.38
     Peny
    0.38
     Kung
    0.37
     homestead
    0.37
    삭
    0.37
     Mess
    0.36
    FindingsResponse
    0.36
    წინ
    0.36
    POSITIVE LOGITS
    rad
    0.55
     rad
    0.52
     RAD
    0.48
    辏
    0.46
    Rad
    0.45
     radia
    0.45
     radiating
    0.45
     радиа
    0.43
     radiated
    0.43
    辐射
    0.42
    Activations Density 0.084%

    No Known Activations