© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 8613
    Prev
    Next
    INDEX
    Explanations

    actions and concepts

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

    income <= 0

    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
     السّ
    0.64
     प्रश्‍
    0.50
    ّر
    0.49
     प्रश्‍न
    0.45
    ጐ
    0.45
     }}^{\
    0.45
    ّد
    0.45
    ّل
    0.42
    ヒ
    0.42
     ಪಿ
    0.42
    POSITIVE LOGITS
     moreover
    0.69
     furthermore
    0.68
     تے
    0.57
     अपन
    0.56
     ampere
    0.54
     adenine
    0.53
     aswell
    0.50
     außerdem
    0.50
     sareng
    0.49
     যাহ
    0.48
    Activations Density 0.192%

    No Known Activations