© 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. 10388
    Prev
    Next
    INDEX
    Explanations

    as you go

    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
    的两
    1.09
     Kimball
    1.06
    бул
    1.06
    🍍
    1.05
     Palin
    1.02
    🍐
    1.01
     cưới
    1.01
     flaming
    1.01
    🍰
    1.00
     artich
    0.99
    POSITIVE LOGITS
     spent
    1.44
     Spent
    1.32
    spent
    1.29
     wasted
    1.25
    Spent
    1.15
    Reserved
    1.14
     expended
    1.07
     waste
    1.04
     wastes
    1.03
     spend
    1.01
    Activations Density 0.292%

    No Known Activations