© 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. 16-GEMMASCOPE-2-RES-262K
    7. 4602
    Prev
    Next
    INDEX
    Explanations

    preserving knowledge, texture, or flavor

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    a
    1.53
    l
    1.18
    c
    1.13
    an
    1.09
    t
    1.02
    0
    0.92
    見
    0.90
     a
    0.90
    あ
    0.90
     the
    0.89
    POSITIVE LOGITS
    ו
    1.48
    و
    1.38
    ן
    1.23
    ומי
    1.12
    יא
    1.10
    I
    1.10
    ל
    1.10
    תה
    0.96
    ווע
    0.93
    ри
    0.93
    Activations Density 0.005%

    No Known Activations