© 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. 81859
    Prev
    Next
    INDEX
    Explanations

    before

    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
    %)
    0.50
     компетен
    0.46
     कराएंगे
    0.44
     брат
    0.43
    規範
    0.43
     yatha
    0.43
     commandBuffer
    0.43
     тощо
    0.43
    ጠን
    0.43
     மின்ன
    0.43
    POSITIVE LOGITS
    亚
    0.48
     seul
    0.44
     escult
    0.39
     desiderio
    0.38
     Street
    0.38
    ége
    0.37
     celebrity
    0.37
     Comercial
    0.37
    却
    0.37
     mercado
    0.36
    Activations Density 0.006%

    No Known Activations