© 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. 8589
    Prev
    Next
    INDEX
    Explanations

    UI component layout

    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
    计量
    1.26
     Rutherford
    1.19
     kick
    1.13
     quantifier
    1.12
    リスク
    1.11
     queryString
    1.11
     jabs
    1.10
    信
    1.09
     বিদ্রোহ
    1.08
    payer
    1.07
    POSITIVE LOGITS
     layout
    1.96
     layouts
    1.91
     Layout
    1.87
     화면
    1.84
     tampilan
    1.79
     dekor
    1.75
     aparência
    1.70
    layout
    1.69
     edifício
    1.67
     aesthetically
    1.66
    Activations Density 0.274%

    No Known Activations