© 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. 410
    Prev
    Next
    INDEX
    Explanations

    numbers and technical details

    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
     đẩy
    1.68
     több
    1.42
    ử
    1.40
     hồ
    1.39
     zwycię
    1.39
     certes
    1.38
     mày
    1.36
     nạn
    1.33
     buton
    1.32
     incendio
    1.32
    POSITIVE LOGITS
    。
    1.96
    ۔
    1.86
    .
    1.71
    .¹
    1.68
    。<
    1.64
    。《
    1.61
    .。
    1.59
    .<
    1.51
    。(
    1.49
    .[[
    1.48
    Activations Density 0.000%

    No Known Activations