© 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. 13-GEMMASCOPE-2-RES-16K
    7. 6392
    Prev
    Next
    INDEX
    Explanations

    protection from or against

    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
    else
    0.95
    changing
    0.86
    elses
    0.77
    ราช
    0.75
    ії
    0.73
    ily
    0.73
    shan
    0.71
    黎
    0.71
    omes
    0.70
    jes
    0.69
    POSITIVE LOGITS
     inscrit
    1.47
     gebra
    1.45
    缎
    1.36
    筺
    1.36
     Ubuy
    1.35
     ανάπτυ
    1.34
    پيديا
    1.33
     videomuzda
    1.32
     presentó
    1.32
     kttt
    1.32
    Activations Density 0.031%

    No Known Activations