© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 15846
    Prev
    Next
    INDEX
    Explanations

    ordering and ranking

    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
    ضة
    0.94
     luas
    0.92
     విస్త
    0.91
     প্রকল্পে
    0.91
    夠
    0.89
     formes
    0.87
    wra
    0.87
    ৃত
    0.86
     habrá
    0.85
    够
    0.84
    POSITIVE LOGITS
    优先级
    1.75
     Ranking
    1.71
     Ranked
    1.71
     rankings
    1.68
     Sorting
    1.65
     sortBy
    1.62
    rank
    1.62
     priority
    1.61
     ranking
    1.60
    顺序
    1.58
    Activations Density 0.095%

    No Known Activations