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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8802
    Prev
    Next
    INDEX
    Explanations

    col + league, Colab, colonial, Colossus, colony

    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
     XIII
    1.07
     XII
    0.99
     সাল
    0.95
     XVI
    0.94
     చెప్పారు
    0.90
     -.
    0.88
    꿇
    0.88
     oy
    0.88
    Czechoslovakia
    0.88
     -,
    0.88
    POSITIVE LOGITS
     полноцен
    0.74
     leis
    0.73
     alcoved
    0.72
     Chances
    0.72
    配
    0.71
     Harmon
    0.70
     বয়ে
    0.70
    proper
    0.69
    本格
    0.69
     snug
    0.69
    Activations Density 0.052%

    No Known Activations