© 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. 1523
    Prev
    Next
    INDEX
    Explanations

    communication channels and information

    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
     উত্তর
    1.67
    Ꭳ
    1.63
     ತಯ
    1.60
    ྜ
    1.56
    쳏
    1.54
    Ꮵ
    1.48
     despertar
    1.46
     জিজ্ঞ
    1.46
    ൨
    1.44
    elez
    1.44
    POSITIVE LOGITS
    ambient
    1.42
    ression
    1.32
    three
    1.31
    payers
    1.30
    olding
    1.28
    external
    1.28
    payer
    1.28
    owe
    1.24
    addie
    1.23
    anti
    1.22
    Activations Density 0.000%

    No Known Activations