© 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. 141313
    Prev
    Next
    INDEX
    Explanations

    retellings and adaptations

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

    reimagining stories and content

    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
     Xt
    0.45
    収録
    0.40
     ქვე
    0.39
     کلی
    0.39
     acumul
    0.39
    中期
    0.39
    促
    0.39
    쌓
    0.39
     macro
    0.38
    郊
    0.38
    POSITIVE LOGITS
     retelling
    0.90
     reimag
    0.76
     adaptations
    0.75
     adaptation
    0.67
    adaptation
    0.67
     reinterpret
    0.65
    版本
    0.62
     version
    0.60
     interpretations
    0.60
     reim
    0.59
    Activations Density 0.199%

    No Known Activations