© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 15944
    Prev
    Next
    INDEX
    Explanations

    why or why not

    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
    Alexander
    1.41
    Danny
    1.40
    Thomas
    1.39
    Benjamin
    1.39
    -/
    1.35
    McDonald
    1.32
    Americans
    1.32
    James
    1.32
    Malcolm
    1.32
    ◊
    1.30
    POSITIVE LOGITS
     Sich
    1.13
     Conservancy
    1.10
     Prinzip
    0.99
    ova
    0.98
     Kuchen
    0.97
    лова
    0.96
    вата
    0.96
     Shand
    0.96
    yi
    0.93
     Werke
    0.93
    Activations Density 0.005%

    No Known Activations