© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 215281
    Prev
    Next
    INDEX
    Explanations

    describing service tiers or features

    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
    ongs
    0.40
    4
    0.39
    Routed
    0.38
     каждую
    0.38
     были
    0.37
    Divider
    0.37
     interag
    0.37
    override
    0.36
    ud
    0.36
    ությ
    0.36
    POSITIVE LOGITS
     Jakarta
    0.41
    Ձ
    0.41
    駅から
    0.40
     riguarda
    0.39
    ですので
    0.39
     အရ
    0.39
    ಜು
    0.39
     সম্ভাব্য
    0.38
     étrangères
    0.38
     biocompat
    0.38
    Activations Density 0.002%

    No Known Activations