© 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. 90923
    Prev
    Next
    INDEX
    Explanations

    insurance, payment, quality

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

    conclusions, implications, or conditional statements

    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
     orchestrated
    0.45
     توقع
    0.44
     amicable
    0.44
     TÜ
    0.43
    Statistical
    0.42
     conjoint
    0.42
    deficit
    0.41
    お店
    0.40
     друже
    0.40
     ਤ
    0.40
    POSITIVE LOGITS
     CryptoJS
    0.49
    污染
    0.46
     Chromatogr
    0.46
     sắc
    0.46
    κρα
    0.45
    же
    0.45
    便
    0.44
    गति
    0.44
    絖
    0.44
    伤害
    0.44
    Activations Density 0.001%

    No Known Activations