© 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-65K
    7. 444
    Prev
    Next
    INDEX
    Explanations

    common examples

    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_65k_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
    ...
    0.87
    …
    0.80
    :
    0.78
    (?)
    0.74
    -
    0.72
    /
    0.72
    .
    0.67
    ./
    0.65
    isit
    0.65
    #
    0.65
    POSITIVE LOGITS
     이러한
    2.01
     Therefore
    1.72
     Advantages
    1.72
     因此
    1.64
     Moreover
    1.63
     例如
    1.63
     또한
    1.61
     Conversely
    1.57
     Generally
    1.57
    此外
    1.57
    Activations Density 1.859%

    No Known Activations