© 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. 31-GEMMASCOPE-2-RES-262K
    7. 47459
    Prev
    Next
    INDEX
    Explanations

    three or more

    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_31_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
    Blogs
    0.45
     trimmed
    0.41
     accompagné
    0.41
     thorough
    0.40
    ارق
    0.39
    inching
    0.38
    e
    0.38
     preced
    0.38
    いただき
    0.37
     aides
    0.37
    POSITIVE LOGITS
    碰到
    0.53
    三种
    0.50
     দিবে
    0.50
    三個
    0.50
     chh
    0.50
     három
    0.47
     వరకు
    0.45
    ד
    0.45
     three
    0.45
    ಞ
    0.44
    Activations Density 0.000%

    No Known Activations