© 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. 127443
    Prev
    Next
    INDEX
    Explanations

    financial capability or reserve

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

    trade, regulatory, statistics, concepts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     false
    0.46
    2
    0.43
     isole
    0.42
    い
    0.41
     aftermarket
    0.41
     ratchet
    0.41
    PROBLEM
    0.41
    Problem
    0.40
     maroon
    0.40
    Pl
    0.40
    POSITIVE LOGITS
     मल्टीप्लिकेशन
    0.50
    énez
    0.48
     അദ്ദേ
    0.47
     vuttam
    0.47
     ربنا
    0.46
     嗯
    0.46
     منٹو
    0.45
    र्वेद
    0.45
    اللہ
    0.45
     файла
    0.44
    Activations Density 0.001%

    No Known Activations