© 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. 53-GEMMASCOPE-2-RES-262K
    7. 62335
    Prev
    Next
    INDEX
    Explanations

    // Example for

    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_53_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    mesh
    0.37
    えられる
    0.37
    toolStripButton
    0.36
    িল্ল
    0.35
    =":
    0.35
     индек
    0.35
    meshes
    0.35
    inoc
    0.35
    rashed
    0.35
    たま
    0.35
    POSITIVE LOGITS
     Opp
    0.40
     weniger
    0.38
    nio
    0.38
     reps
    0.37
    trasound
    0.36
    บัน
    0.36
    …’
    0.35
    쨰
    0.35
     Fewer
    0.35
     shrinks
    0.35
    Activations Density 0.002%

    No Known Activations