© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 21345
    Prev
    Next
    INDEX
    Explanations

    happiness of mind

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

    reason and effect

    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
     Ünivers
    0.63
    摭
    0.59
    üsse
    0.58
     Mö
    0.57
     vermutlich
    0.56
     Metall
    0.54
    üksek
    0.54
     aşağı
    0.54
     sowohl
    0.54
    ल्पन
    0.53
    POSITIVE LOGITS
     bahut
    0.66
     ਚ
    0.66
     ਹੈ
    0.65
     ਰ
    0.65
     ਤ
    0.65
     ਮ
    0.65
     ਇ
    0.63
     chhoti
    0.63
     ਜ
    0.62
     ਉਨ੍ਹਾਂ
    0.61
    Activations Density 0.027%

    No Known Activations