© 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. 87516
    Prev
    Next
    INDEX
    Explanations

    AI Collective

    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
     Clamp
    0.39
     Attorney
    0.39
     Schroeder
    0.38
    情报
    0.38
     Wad
    0.37
     সফ
    0.36
     Eck
    0.36
     ワ
    0.35
    สาย
    0.34
     Conta
    0.34
    POSITIVE LOGITS
    sparsebundle
    0.45
     hourglass
    0.44
     cillum
    0.40
    hourglass
    0.39
     сми
    0.39
     hijos
    0.39
     hollow
    0.38
    oracle
    0.38
     dying
    0.37
     રહ
    0.37
    Activations Density 0.001%

    No Known Activations