© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 31475
    Prev
    Next
    INDEX
    Explanations

    sky, stars, constellations, night, astronomy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     repercussions
    0.42
     pyrolysis
    0.42
     माया
    0.40
    تقرير
    0.39
    生ま
    0.39
     circulate
    0.39
     homeostasis
    0.39
    メイド
    0.38
    radiative
    0.38
    揮
    0.38
    POSITIVE LOGITS
     Sky
    0.73
     আকাশের
    0.66
    Sky
    0.64
     nightly
    0.64
     starg
    0.62
     Night
    0.62
     Astronomy
    0.61
     Skies
    0.61
     Noct
    0.59
     Astronom
    0.59
    Activations Density 0.108%

    No Known Activations