© 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. 14674
    Prev
    Next
    INDEX
    Explanations

    explains what the function does

    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
    fifty
    1.49
    (?)
    1.48
     of
    1.47
    ylate
    1.41
    (
    1.40
    nemid
    1.39
     taxa
    1.32
    Lima
    1.32
     historically
    1.31
    5
    1.31
    POSITIVE LOGITS
     verrou
    1.85
     impegn
    1.83
     hoạt
    1.81
     Aufenthalt
    1.80
     impegno
    1.78
    SDLCheck
    1.75
     funzionamento
    1.75
     duração
    1.74
     अध्यक्षता
    1.74
     arbete
    1.72
    Activations Density 0.097%

    No Known Activations