© 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. 205607
    Prev
    Next
    INDEX
    Explanations

    oscilloscope and multimeter

    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
    רה
    0.54
    ку
    0.52
    Heb
    0.52
    지
    0.51
    ب
    0.51
    เว
    0.48
    ه
    0.48
    ان
    0.48
    ต์
    0.47
    ש
    0.46
    POSITIVE LOGITS
     absorbent
    0.48
     x
    0.48
     saffron
    0.47
     aphids
    0.46
     Academy
    0.45
     panch
    0.44
     ph
    0.44
     ammonia
    0.44
     shrimps
    0.44
     nurses
    0.43
    Activations Density 0.006%

    No Known Activations