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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 8681
    Prev
    Next
    INDEX
    Explanations

    javascript code generation

    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
     devi
    1.79
    cionario
    1.76
     ^{\
    1.73
     Rewrite
    1.69
     indetermin
    1.67
     sloppy
    1.67
     fant
    1.67
    yorum
    1.67
     reagents
    1.66
     Totally
    1.65
    POSITIVE LOGITS
    $^{
    3.07
    ly
    2.57
    rt
    2.44
    ুগত্য
    2.39
    শিয়া
    2.24
    വർ
    2.12
    प्रकाश
    2.08
     kerja
    2.06
    pronged
    2.06
    ryk
    2.03
    Activations Density 0.062%

    No Known Activations