© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7590
    Prev
    Next
    INDEX
    Explanations

    serious crime or breach

    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
     Brust
    0.86
     flank
    0.81
     gear
    0.78
    forderung
    0.78
    彻
    0.75
    ciąż
    0.74
     pret
    0.74
     olmadığını
    0.74
     অভিম
    0.74
     nost
    0.74
    POSITIVE LOGITS
    fasta
    1.03
     सा
    0.95
    人用
    0.94
    uiDesigner
    0.94
     LoginPage
    0.90
    (".");
    0.90
    FileUtils
    0.90
     যতক্ষণ
    0.90
    erapeut
    0.88
     רא
    0.88
    Activations Density 0.013%

    No Known Activations