© 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. 40-GEMMASCOPE-2-RES-262K
    7. 29541
    Prev
    Next
    INDEX
    Explanations

    css border property

    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_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
    墂
    0.41
    ൮
    0.40
    㹂
    0.40
    丝
    0.40
    boundaries
    0.39
    퐶
    0.38
    schluss
    0.38
    长江
    0.38
    सीमा
    0.38
    溲
    0.37
    POSITIVE LOGITS
     person
    0.46
     adipisicing
    0.45
    badbreak
    0.45
     Person
    0.41
     adipis
    0.41
     Euler
    0.40
    gaussian
    0.39
    normally
    0.39
     mic
    0.39
     هز
    0.38
    Activations Density 0.002%

    No Known Activations