© 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. 16000
    Prev
    Next
    INDEX
    Explanations

    passing data or arguments

    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
     aritmética
    1.20
     Schur
    1.12
     lógica
    1.10
    وترات
    1.09
     mene
    1.09
     Puis
    1.07
     reunión
    1.05
    Ｖ
    1.04
     nodig
    1.03
     Satur
    1.03
    POSITIVE LOGITS
     приве
    1.09
    现金
    1.06
     seized
    1.05
    essel
    1.03
     collectible
    1.01
     prize
    1.00
     bottle
    0.99
     collection
    0.98
     collected
    0.97
    Goods
    0.95
    Activations Density 0.218%

    No Known Activations