© 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. 17-GEMMASCOPE-2-RES-16K
    7. 1109
    Prev
    Next
    INDEX
    Explanations

    name is

    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_17_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
     &/
    1.93
     हेतु
    1.81
     אך
    1.80
     лишь
    1.79
     此
    1.73
     已
    1.71
    !(
    1.71
     تنها
    1.70
    !.
    1.69
    ()/
    1.69
    POSITIVE LOGITS
     [
    2.89
    っていう
    2.73
     그다음에
    2.33
    んですけど
    2.26
     yeah
    2.17
     somebody
    2.16
     really
    2.13
     uh
    2.11
     everybody
    2.10
    -[
    2.06
    Activations Density 2.422%

    No Known Activations