© 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. 16-GEMMASCOPE-2-RES-262K
    7. 106594
    Prev
    Next
    INDEX
    Explanations

    scientific notation

    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_16_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
     Siles
    0.53
    רי
    0.52
     PLANT
    0.50
    वुड
    0.50
    таў
    0.50
    라
    0.50
    би
    0.49
    лосо
    0.47
    ູ
    0.47
    בו
    0.47
    POSITIVE LOGITS
     لل
    0.51
     וי
    0.49
     задума
    0.49
     یاد
    0.49
     വാഹന
    0.49
     বৈ
    0.48
    December
    0.48
     πρό
    0.48
     δή
    0.48
    MSFontService
    0.48
    Activations Density 0.000%

    No Known Activations