© 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. 13-GEMMASCOPE-2-RES-16K
    7. 11769
    Prev
    Next
    INDEX
    Explanations

    C++ code structures

    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
    पचारिक
    1.52
    ürlich
    1.45
    న్
    1.43
    userdetails
    1.41
    নীতির
    1.40
    zeugt
    1.35
    諌
    1.35
    userService
    1.34
     adenos
    1.33
     मुकाबला
    1.32
    POSITIVE LOGITS
     year
    1.22
     onwards
    1.16
    YEAR
    1.15
    year
    1.08
     month
    1.06
    1.04
     Medio
    1.02
     months
    1.01
    下旬
    1.00
     прошлого
    0.99
    Activations Density 0.197%

    No Known Activations