© 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. 185436
    Prev
    Next
    INDEX
    Explanations

    an other

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

    Watch backups

    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
     petting
    0.48
     petrochemical
    0.46
     biotech
    0.45
    ঘন
    0.44
     essential
    0.44
     transgene
    0.44
    ক্ষণে
    0.43
    α
    0.43
    റേ
    0.43
     collectors
    0.42
    POSITIVE LOGITS
     любое
    0.55
     любые
    0.50
    Fem
    0.49
     любую
    0.49
     정도
    0.48
     أي
    0.47
     יש
    0.46
     שי
    0.45
     تسجيل
    0.45
    藓
    0.45
    Activations Density 0.000%

    No Known Activations