© 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. 1520
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     stupe
    1.81
     மாய
    1.59
     mete
    1.59
     tritt
    1.51
    राने
    1.48
     داخلی
    1.48
    ̊
    1.46
     화
    1.45
    ̉a
    1.44
    년
    1.43
    POSITIVE LOGITS
     [&](
    1.83
    defaults
    1.78
    क्षकों
    1.65
     yolks
    1.65
    avings
    1.60
     [](
    1.59
    ectors
    1.59
    ives
    1.58
    eburger
    1.58
    viamente
    1.58
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.