© 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. 40907
    Prev
    Next
    INDEX
    Explanations

    for Airports, for Justice

    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
     भै
    0.37
     Shine
    0.35
    哞
    0.35
     approxim
    0.34
     എന്നിവ
    0.34
    ronectin
    0.34
    itting
    0.33
     സ്ത്രീ
    0.33
    ඵ
    0.33
    জিন
    0.32
    POSITIVE LOGITS
     thought
    0.59
     days
    0.55
    thought
    0.55
     armies
    0.53
     Thought
    0.52
    Thought
    0.52
     চিন্ত
    0.51
     jours
    0.49
    ewords
    0.47
     душа
    0.47
    Activations Density 0.003%

    No Known Activations