© 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. 71265
    Prev
    Next
    INDEX
    Explanations

    essay topics

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

    City of, silent hill nurse

    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
     greatness
    0.48
    channel
    0.48
    บ
    0.48
     quarrel
    0.47
    ตัดสิน
    0.45
    츈
    0.45
     enormously
    0.45
    était
    0.44
     utilizz
    0.44
    ประตู
    0.44
    POSITIVE LOGITS
     შორის
    0.47
     كلمات
    0.46
     InputStream
    0.45
    名字
    0.44
     سنة
    0.44
    𝙣
    0.43
    涵盖
    0.42
     نام
    0.42
     PQ
    0.42
     تلق
    0.42
    Activations Density 0.001%

    No Known Activations