© 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
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1380
    Prev
    Next
    INDEX
    Explanations

    citizens observing, understanding how

    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_65k_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
    ịnh
    1.11
     मल्
    1.08
     söz
    1.05
    දන
    1.03
    ửa
    1.02
     proprietà
    1.00
    මට
    1.00
    ත
    0.99
     hàm
    0.99
    දි
    0.98
    POSITIVE LOGITS
    permanent
    0.75
     total
    0.75
     specific
    0.74
     negative
    0.73
     overly
    0.73
    負
    0.73
     subjug
    0.72
     sometimes
    0.71
     non
    0.71
     positive
    0.70
    Activations Density 0.000%

    No Known Activations