© 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. 9305
    Prev
    Next
    INDEX
    Explanations

    . Here

    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
    द्
    0.35
     Choose
    0.35
     Aztec
    0.34
     fala
    0.33
     Lavender
    0.33
     Gertrude
    0.32
     agar
    0.32
     Oni
    0.32
    薦
    0.32
     Alberta
    0.32
    POSITIVE LOGITS
     그리고
    0.45
    그리고
    0.44
    लेकिन
    0.41
    そして
    0.40
    とその
    0.37
    (;
    0.36
    以及
    0.35
     لكن
    0.34
    所以
    0.34
     вули
    0.34
    Activations Density 0.116%

    No Known Activations