© 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. 478
    Prev
    Next
    INDEX
    Explanations

    this and following context

    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
    rutt
    1.64
     назвать
    1.58
    sine
    1.53
    ждением
    1.51
    setString
    1.50
    cussion
    1.48
     ngữ
    1.48
    ሶ
    1.45
    걀
    1.45
    asambhavam
    1.44
    POSITIVE LOGITS
     firsthand
    1.68
     rost
    1.51
    ധിപ
    1.51
    खी
    1.50
     vins
    1.49
     congruence
    1.42
     glimpses
    1.42
    ান্য
    1.41
     blurry
    1.41
    ed
    1.41
    Activations Density 0.590%

    No Known Activations