© 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. 12000
    Prev
    Next
    INDEX
    Explanations

    Say "yes" or "no"

    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
    
    1.59
     hoạt
    1.45
    ových
    1.45
     các
    1.43
     분야
    1.42
     ডিভাই
    1.41
     विभाग
    1.40
    -,
    1.39
     및
    1.39
     기능을
    1.38
    POSITIVE LOGITS
    Sorry
    1.54
     fucking
    1.47
     Bless
    1.33
     fuck
    1.32
    Fuck
    1.32
     pecados
    1.32
     crucified
    1.29
     humild
    1.29
    Winner
    1.29
     Murder
    1.29
    Activations Density 0.057%

    No Known Activations