© 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. 10218
    Prev
    Next
    INDEX
    Explanations

    Lambda function

    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
    i
    1.08
     прямой
    1.02
     monopole
    1.01
    iiv
    1.00
    धीर
    0.98
    is
    0.98
     зависи
    0.98
     зависимости
    0.96
     quelconque
    0.93
    iis
    0.93
    POSITIVE LOGITS
     因此
    1.61
    των
    1.36
     therefore
    1.35
    therefore
    1.33
    所以我
    1.32
    ㄲ
    1.27
    因此
    1.24
     所以
    1.23
    ểu
    1.22
     thus
    1.21
    Activations Density 0.000%

    No Known Activations