© 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. 1578
    Prev
    Next
    INDEX
    Explanations

    Option followed by number

    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
    在大
    1.01
    栆
    0.99
    在一个
    0.94
    いたら
    0.90
    ઍ
    0.90
    getvalue
    0.89
    桕
    0.88
    នៅ
    0.87
    কিছু
    0.87
    вает
    0.87
    POSITIVE LOGITS
     III
    1.57
    Ⅲ
    1.54
     II
    1.51
    Ⅱ
    1.42
     XXI
    1.41
    III
    1.40
     VII
    1.39
     XIII
    1.37
     XXII
    1.33
    1
    1.32
    Activations Density 0.709%

    No Known Activations