© 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-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 8794
    Prev
    Next
    INDEX
    Explanations

    understanding the problem

    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_16k_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
     о
    1.05
     п
    0.93
    iop
    0.91
     О
    0.90
    к
    0.90
     ขณะ
    0.88
     б
    0.87
     Вам
    0.87
    يته
    0.85
    іо
    0.84
    POSITIVE LOGITS
    ங்குகள்
    1.53
     गर्ने
    1.40
    Triangle
    1.39
    triangle
    1.34
    FormProvider
    1.33
    作成
    1.32
    ابات
    1.27
     menerima
    1.26
    ਊ
    1.26
     pathogenesis
    1.26
    Activations Density 0.000%

    No Known Activations