© 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. 146563
    Prev
    Next
    INDEX
    Explanations

    connectedness with God and prayer

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

    introduces details

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Business
    0.48
    t
    0.46
    Business
    0.46
     Industrial
    0.45
     '',
    0.44
     C
    0.44
     Great
    0.43
    ционное
    0.43
     Ronaldo
    0.42
     Amazing
    0.41
    POSITIVE LOGITS
    用於
    0.57
     shod
    0.55
    ｲ
    0.55
    綰
    0.54
    균
    0.52
    ਿਤ
    0.51
    봇
    0.50
    べ
    0.48
    莢
    0.47
    칸
    0.47
    Activations Density 0.000%

    No Known Activations