© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9834
    Prev
    Next
    INDEX
    Explanations

    code and programming tasks

    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_16k_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
    カート
    0.46
     stethoscope
    0.44
     منتقل
    0.44
     वर्षा
    0.43
     Shun
    0.42
    らっしゃ
    0.42
    soe
    0.42
    雨
    0.41
     tunt
    0.41
    ne
    0.40
    POSITIVE LOGITS
    پیگنڈ
    0.45
    тивы
    0.43
     боюнча
    0.43
     ரஷ்ய
    0.43
     bizony
    0.42
    зы
    0.41
    سين
    0.40
    बादी
    0.40
    емой
    0.40
    świad
    0.40
    Activations Density 0.030%

    No Known Activations