© 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. 5058
    Prev
    Next
    INDEX
    Explanations

    replace with

    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
    Созда
    1.69
     Teknologi
    1.68
    rimin
    1.66
     Technik
    1.65
    ⿺
    1.62
    witter
    1.60
    ler
    1.60
    leri
    1.60
    proses
    1.58
    े
    1.58
    POSITIVE LOGITS
     substituir
    1.92
    కీయ
    1.86
    faithful
    1.83
     строк
    1.78
    <bos>
    1.71
     zeggen
    1.69
    替换
    1.69
     sustit
    1.69
    তান্ত্রিক
    1.67
    ็ง
    1.62
    Activations Density 0.237%

    No Known Activations