© 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. 152884
    Prev
    Next
    INDEX
    Explanations

    the stars, heavens, planets

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

    cultural implications, potential impact, those pictures

    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
    樊
    0.48
    cienza
    0.46
    యంలో
    0.45
    gana
    0.45
    ຕະ
    0.43
     Kej
    0.42
    𝑺
    0.42
    mino
    0.41
     вме
    0.40
    zać
    0.40
    POSITIVE LOGITS
    នៅ
    0.48
     মাথায়
    0.47
     የ
    0.46
     socialism
    0.43
     বৃষ্টির
    0.43
    Tax
    0.43
     ه
    0.42
     মাথায়
    0.42
     lluvias
    0.42
     가족
    0.42
    Activations Density 0.002%

    No Known Activations