© 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. 6425
    Prev
    Next
    INDEX
    Explanations

    support groups

    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
     inkább
    0.94
     comunque
    0.93
    겸
    0.91
    öm
    0.90
    െന്ന്
    0.89
    兼
    0.84
    もう少し
    0.82
     shouldn
    0.80
     Wasn
    0.79
    趁
    0.78
    POSITIVE LOGITS
    부터
    1.73
     부터
    1.67
     الى
    1.58
    到
    1.58
     hasta
    1.58
    到现在
    1.55
     onwards
    1.54
    まで
    1.53
     إلى
    1.50
     đến
    1.50
    Activations Density 0.231%

    No Known Activations