© 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. 10131
    Prev
    Next
    INDEX
    Explanations

    javascript function definitions

    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
     assunto
    1.70
     Ấ
    1.63
     gar
    1.59
     endeavour
    1.51
     cop
    1.50
     pl
    1.50
     manoe
    1.48
     possess
    1.47
     requis
    1.46
     andar
    1.46
    POSITIVE LOGITS
    цыяна
    1.94
    ۶
    1.92
    eryka
    1.83
    แข่ง
    1.82
    ality
    1.81
    iconfont
    1.80
    寂
    1.80
    nal
    1.79
    م
    1.76
    ധിപ
    1.73
    Activations Density 0.000%

    No Known Activations