© 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-16K
    7. 9666
    Prev
    Next
    INDEX
    Explanations

    YouTuber, feature, cost, inequality

    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
     connective
    1.51
    üge
    1.28
    দানি
    1.28
     مدد
    1.26
     terutama
    1.25
     수가
    1.23
    ي
    1.19
     питание
    1.19
    িউ
    1.19
    ссу
    1.18
    POSITIVE LOGITS
    𝐱
    1.78
     lạc
    1.59
    त्रे
    1.51
    fieldName
    1.47
    𝗽
    1.46
    ◔
    1.42
    𝗷
    1.40
    kart
    1.39
    treasure
    1.37
    itemName
    1.36
    Activations Density 0.000%

    No Known Activations