© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 86751
    Prev
    Next
    INDEX
    Explanations

    articles about financial programs

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

    concerns about finance and position

    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
    ഗണ
    0.53
    čno
    0.47
     அதிகரித்து
    0.47
    ි
    0.47
    LLS
    0.46
     dictum
    0.45
     ervan
    0.45
    ouwd
    0.45
    ווה
    0.45
    佐藤
    0.45
    POSITIVE LOGITS
    шения
    0.46
     возмо
    0.43
     मिलेगा
    0.41
     دسترس
    0.40
     भरने
    0.39
     Deluxe
    0.39
     будущего
    0.39
     यंत्र
    0.39
    빠
    0.39
     Mongolia
    0.39
    Activations Density 0.001%

    No Known Activations