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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8426
    Prev
    Next
    INDEX
    Explanations

    support for financial/system/services

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

    support system or groups

    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_53_width_65k_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
    LECTION
    0.37
    ཙ
    0.37
     phục
    0.36
    нды
    0.36
     spots
    0.36
    หม
    0.36
     пропуска
    0.36
     ám
    0.36
    használ
    0.35
    提
    0.35
    POSITIVE LOGITS
     financially
    0.76
     financiero
    0.73
     network
    0.71
    网络的
    0.66
     financière
    0.63
     नेटवर्क
    0.62
    iveness
    0.62
    network
    0.61
     механиз
    0.60
     financiera
    0.59
    Activations Density 0.065%

    No Known Activations