© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6662
    Prev
    Next
    INDEX
    Explanations

    you need or plan

    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
    Negative Logits
    TargetFramework
    0.82
    บ้าง
    0.79
    時
    0.75
     время
    0.72
    院
    0.71
    会在
    0.71
     xổ
    0.70
     আয়াত
    0.70
    ሻ
    0.68
    à
    0.68
    POSITIVE LOGITS
     डिस्प्ले
    0.90
    arity
    0.87
    agiri
    0.85
    جل
    0.82
     Kondo
    0.82
     Telling
    0.80
    फ्र
    0.80
     Strings
    0.80
    arreg
    0.79
     Beg
    0.79
    Activations Density 0.044%

    No Known Activations