© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 790
    Prev
    Next
    INDEX
    Explanations

    winning context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     menghasilkan
    1.75
    휠
    1.75
     법칙
    1.72
     pasangan
    1.70
     jumlah
    1.68
    𝚝
    1.66
     নিষ্ঠুর
    1.63
     ಸುದ್ದಿ
    1.63
    𝘁
    1.61
    억원
    1.59
    POSITIVE LOGITS
     inspirado
    1.26
     elite
    1.22
    くれて
    1.20
    м
    1.16
    ছেন
    1.15
    es
    1.15
     Louis
    1.13
     जवळपास
    1.13
     né
    1.13
     affairs
    1.13
    Activations Density 0.000%

    No Known Activations