© 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-16K
    7. 2380
    Prev
    Next
    INDEX
    Explanations

    HTML, browser, and WebUSB

    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
    ारस
    1.32
    ור
    1.32
    at
    1.32
    eu
    1.30
    ja
    1.30
    ي
    1.28
     private
    1.27
    op
    1.24
    juang
    1.22
     urine
    1.19
    POSITIVE LOGITS
     Reporters
    1.82
     cladding
    1.78
    trav
    1.71
    olulu
    1.69
    ᐸ
    1.68
    incott
    1.67
    ᓵ
    1.66
    
    1.65
    spapers
    1.65
     habis
    1.64
    Activations Density 0.027%

    No Known Activations