© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10789
    Prev
    Next
    INDEX
    Explanations

    months and years

    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
    ப்பட
    1.10
     الاثنين
    1.09
     betekent
    1.04
     底
    1.04
    你們
    1.04
    .}(
    1.03
    Exporter
    1.01
     ไฟล์
    1.01
     ಸಂಬಂಧ
    1.01
    FProperties
    1.00
    POSITIVE LOGITS
     W
    1.12
     N
    1.08
     S
    1.02
     E
    1.01
     w
    0.99
     s
    0.80
     Safari
    0.75
     self
    0.75
     ن
    0.74
    여
    0.73
    Activations Density 0.091%

    No Known Activations