© 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. 108815
    Prev
    Next
    INDEX
    Explanations

    reporting numbers

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

    leading and analyzing actions

    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
    بدا
    0.50
     conifers
    0.47
     anthropology
    0.47
     ampere
    0.46
    一大
    0.46
     classrooms
    0.46
    了出来
    0.45
     uppercase
    0.45
    ographics
    0.45
    岗
    0.45
    POSITIVE LOGITS
     phổi
    0.52
     seç
    0.51
    𝔰
    0.50
     Seç
    0.50
     courtes
    0.48
     칼
    0.48
     uygul
    0.47
     सर्वश्रेष्ठ
    0.47
    aların
    0.47
     regolare
    0.47
    Activations Density 0.000%

    No Known Activations