© 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. 136230
    Prev
    Next
    INDEX
    Explanations

    Day 1-3:

    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
     fashionable
    0.44
     enduro
    0.44
     disable
    0.43
     startups
    0.43
    ഓ
    0.43
     सेल्स
    0.42
     osią
    0.41
    品番
    0.41
     éta
    0.40
     ski
    0.40
    POSITIVE LOGITS
    л
    0.43
     গুরুত্বপূর্ণ
    0.43
    nesset
    0.43
    TOTAL
    0.42
    IRONMENT
    0.42
    পেক্ষ
    0.42
    দিগকে
    0.42
    iliated
    0.42
    少ない
    0.42
    যেমন
    0.41
    Activations Density 0.004%

    No Known Activations