© 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. 180000
    Prev
    Next
    INDEX
    Explanations

    قدیمی، 备份، 9 suns

    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
    ́
    0.44
     Konink
    0.41
    onActivityResult
    0.41
    >′</
    0.40
    é
    0.40
     liv
    0.40
     Nederlands
    0.39
     Buddh
    0.38
    athlet
    0.38
    optimized
    0.38
    POSITIVE LOGITS
     قدیمی
    0.53
    前辈
    0.53
     قدیم
    0.51
     vardı
    0.47
    备份
    0.45
    начально
    0.45
    还有
    0.44
    隐含
    0.44
    是为了
    0.44
    垕
    0.44
    Activations Density 0.000%

    No Known Activations