© 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. 2641
    Prev
    Next
    INDEX
    Explanations

    within scope of programming constructs

    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
    using
    0.90
    得上
    0.84
     using
    0.81
    isis
    0.81
    සුව
    0.80
    «
    0.79
     Which
    0.77
     rispetto
    0.77
    מור
    0.76
    ្ម
    0.75
    POSITIVE LOGITS
     everywhere
    1.48
     haunt
    1.39
     khắp
    1.33
    统治
    1.31
     permeates
    1.25
     Everywhere
    1.22
     lexicon
    1.21
     dominance
    1.20
     interwoven
    1.19
    <unused678>
    1.19
    Activations Density 0.563%

    No Known Activations