© 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. 31-GEMMASCOPE-2-RES-262K
    7. 80337
    Prev
    Next
    INDEX
    Explanations

    hugging face link

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    benefit
    0.44
    ّر
    0.41
    serious
    0.40
    やま
    0.40
    的面
    0.40
    急
    0.40
     benefit
    0.40
    🆓
    0.40
     population
    0.39
     बुल
    0.39
    POSITIVE LOGITS
    ঞ্জ
    0.44
     Operations
    0.43
    itiba
    0.43
     entanto
    0.42
    തിരെ
    0.42
    atasaray
    0.42
    իկ
    0.42
     Сот
    0.42
    ];
    0.42
     difficultés
    0.42
    Activations Density 0.005%

    No Known Activations