© 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
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 88
    Prev
    Next
    INDEX
    Explanations

    fore precede

    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
    -->'
    0.85
     을
    0.79
     -->'
    0.78
     Ан
    0.76
    predictors
    0.75
     명이
    0.74
    峀
    0.74
    孅
    0.73
     WHICH
    0.72
     Пред
    0.71
    POSITIVE LOGITS
    <start_of_image>
    0.81
     également
    0.71
     também
    0.69
    <eos>
    0.66
    。
    0.64
     ebenfalls
    0.63
     versão
    0.58
     Murt
    0.58
    <unused63>
    0.57
    <unused61>
    0.57
    Activations Density 0.000%

    No Known Activations