© 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. 81804
    Prev
    Next
    INDEX
    Explanations

    dates, locations, and replies

    np_acts-logits-general · gemini-2.5-flash-lite

    / followed by certain words

    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
    หรือ
    0.72
     veya
    0.63
    或
    0.59
    或者
    0.55
     किंवा
    0.54
    🌆
    0.54
     atau
    0.52
     অথবা
    0.52
     oppure
    0.50
     hoặc
    0.50
    POSITIVE LOGITS
     основе
    0.44
     टकराव
    0.43
     रे
    0.42
    ỉ
    0.41
    ă
    0.41
    }$)
    0.40
     देहरादून
    0.40
     타고
    0.39
     लेफ्ट
    0.39
     androidx
    0.38
    Activations Density 0.003%

    No Known Activations