© 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. 87182
    Prev
    Next
    INDEX
    Explanations

    food, restaurants, and commerce

    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
    Not in Any Lists

    No Comments

    Negative Logits
    疖
    0.38
     difficultés
    0.37
    र्ण
    0.36
    品の
    0.36
    قيقة
    0.36
     Kurdish
    0.36
     カー
    0.35
     कर्तव्यों
    0.35
     જરૂરી
    0.35
    啬
    0.35
    POSITIVE LOGITS
     Mocha
    0.47
    就算是
    0.41
     Chocol
    0.41
     INDI
    0.40
     even
    0.40
     Even
    0.39
     suddenly
    0.39
     roughly
    0.39
     brick
    0.38
    Mozilla
    0.38
    Activations Density 0.003%

    No Known Activations