© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 55301
    Prev
    Next
    INDEX
    Explanations

    Saudi Crown Prince

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

    business and financial terms

    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
     nonché
    0.42
    ம்
    0.41
     καθώς
    0.41
    cı
    0.40
     vague
    0.40
    0
    0.40
    ướ
    0.39
     기울
    0.39
    ENTRY
    0.39
    eflow
    0.39
    POSITIVE LOGITS
     वित्तीय
    0.46
     promoção
    0.45
     xong
    0.43
     promozione
    0.43
     rebate
    0.42
     этому
    0.42
     commissioners
    0.41
     financier
    0.41
     நிய
    0.41
     rebates
    0.41
    Activations Density 0.002%

    No Known Activations