© 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
    2. Gemma-3-1B
    3. 22-GEMMASCOPE-2-RES-16K
    4. 926
    Prev
    Next
    INDEX
    Explanations

    index i or ordinal numbers

    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_22_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
    城的
    0.90
     gql
    0.85
     விதைகள்
    0.84
    城
    0.82
     ))}
    0.79
    াবু
    0.78
     weniger
    0.78
     minder
    0.78
    轲
    0.77
     城
    0.77
    POSITIVE LOGITS
    th
    2.38
    rd
    2.30
    nd
    2.08
    st
    1.89
    sth
    1.76
    nth
    1.73
    <sup>
    1.70
    thand
    1.67
    rst
    1.65
    ème
    1.55
    Activations Density 0.929%

    No Known Activations