© 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. 31-GEMMASCOPE-2-RES-262K
    7. 74623
    Prev
    Next
    INDEX
    Explanations

    export default

    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
    Negative Logits
    อาหาร
    0.53
    ])$
    0.47
     இவற்ற
    0.46
     aquaculture
    0.46
     déjeuner
    0.46
     carbure
    0.44
     archaic
    0.44
     တို့
    0.44
    expec
    0.43
     wafer
    0.43
    POSITIVE LOGITS
    dia
    0.44
    u
    0.40
    itmen
    0.39
    <0x9F>
    0.39
    дный
    0.38
    ed
    0.37
    ät
    0.37
    جا
    0.37
    mars
    0.37
    r
    0.37
    Activations Density 0.001%

    No Known Activations