© 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. 87481
    Prev
    Next
    INDEX
    Explanations

    creature, compare, height, a, painstakingly, modeling, PDF, history

    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
     Shuttle
    0.44
     dislocation
    0.41
     shuttle
    0.40
    낄
    0.39
     aggravate
    0.39
    喤
    0.39
    calibration
    0.38
     спе
    0.38
     acquistare
    0.38
     \%)$.
    0.38
    POSITIVE LOGITS
     hab
    0.46
     morally
    0.38
     socially
    0.37
     nonetheless
    0.37
     comfy
    0.37
    踏
    0.37
    第二百
    0.37
     Habib
    0.36
    ឃើញ
    0.36
     vrij
    0.36
    Activations Density 0.001%

    No Known Activations