© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 232455
    Prev
    Next
    INDEX
    Explanations

    African terms and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     حرکت
    0.54
     نهایت
    0.50
     INDUST
    0.49
    ğ
    0.48
    URNIZOR
    0.47
    ⤦
    0.47
     Қ
    0.47
     decompression
    0.46
     গ্রামবাস
    0.46
    ｘ
    0.46
    POSITIVE LOGITS
    templates
    0.54
    African
    0.49
    Downloaded
    0.49
     expon
    0.48
    requires
    0.47
    dit
    0.46
    Nin
    0.46
     ess
    0.46
    expires
    0.46
     Africans
    0.45
    Activations Density 0.000%

    No Known Activations