© 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. 176951
    Prev
    Next
    INDEX
    Explanations

    Grace of God

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

    loneliness, hackathons, mother tongue

    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
    ੇ
    0.48
     LEN
    0.48
    ная
    0.47
    ITAS
    0.47
     JANUARY
    0.47
    АН
    0.46
    府
    0.46
    จ
    0.44
    కు
    0.43
    僅
    0.43
    POSITIVE LOGITS
     Modify
    0.44
     ثبت
    0.42
     frustrated
    0.41
     Synchron
    0.41
     மணியே
    0.41
     avoid
    0.40
     Mith
    0.40
     Eliminate
    0.40
     Diff
    0.40
     remove
    0.40
    Activations Density 0.001%

    No Known Activations