© 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. 2425
    Prev
    Next
    INDEX
    Explanations

    rather than

    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
     également
    0.39
    くなった
    0.38
    ம்
    0.38
    แต่
    0.35
     WITHOUT
    0.34
     എന്നാൽ
    0.33
     xhrObj
    0.33
     altre
    0.33
     ಬಹಳ
    0.33
    ️
    0.32
    POSITIVE LOGITS
     being
    0.39
     an
    0.39
     simply
    0.38
     trying
    0.36
    review
    0.35
    。\
    0.34
    MER
    0.33
    être
    0.33
     merely
    0.33
    resist
    0.32
    Activations Density 0.034%

    No Known Activations