© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 119146
    Prev
    Next
    INDEX
    Explanations

    cut corners

    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
     hoofd
    0.55
     tino
    0.53
    ﺒ
    0.53
     oficial
    0.50
    ﾆ
    0.50
    اري
    0.50
     alcoholic
    0.50
     mente
    0.49
     in
    0.49
     progetto
    0.49
    POSITIVE LOGITS
    మై
    0.61
     ItemStack
    0.55
     ciências
    0.54
    𒃶
    0.53
    漫
    0.52
    科学
    0.51
     typesetting
    0.51
    动漫
    0.51
     Sahel
    0.51
     It
    0.50
    Activations Density 0.000%

    No Known Activations