© 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. 15885
    Prev
    Next
    INDEX
    Explanations

    Okay, here are

    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
     anew
    0.86
    .
    0.79
     venturing
    0.75
    ।
    0.73
    loos
    0.72
    coll
    0.70
     lively
    0.70
     char
    0.69
    В
    0.68
     discret
    0.68
    POSITIVE LOGITS
     cette
    1.51
     이렇게
    1.47
    这样一个
    1.47
     questo
    1.46
     tohoto
    1.45
     цієї
    1.42
     මෙම
    1.41
     questa
    1.41
     această
    1.41
     queste
    1.39
    Activations Density 0.350%

    No Known Activations