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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9016
    Prev
    Next
    INDEX
    Explanations

    introductions to new concepts

    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
    dbcontext
    1.58
    㞖
    1.58
    <unused1679>
    1.58
    <unused425>
    1.58
    <unused1025>
    1.57
    <unused381>
    1.56
    <unused1959>
    1.53
    <unused1672>
    1.53
    <unused424>
    1.52
     iccad
    1.51
    POSITIVE LOGITS
     invention
    1.35
     inventions
    1.08
     inventors
    1.02
     therefore
    0.96
     inventive
    0.94
     improved
    0.93
    发明
    0.87
     patented
    0.86
     variantes
    0.85
    us
    0.82
    Activations Density 0.112%

    No Known Activations