© 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. 10623
    Prev
    Next
    INDEX
    Explanations

    Good for or if

    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
     palab
    0.81
     ribbons
    0.78
    帛
    0.77
    รอ
    0.76
     bala
    0.75
     cuma
    0.75
     ribbon
    0.74
    รือ
    0.74
     simul
    0.73
     Ribbon
    0.72
    POSITIVE LOGITS
     unforeseen
    1.39
     cambiamenti
    1.23
     воспита
    1.14
     cambiamento
    1.12
     acontecimientos
    1.10
    の変化
    1.09
     changes
    1.08
    unexpected
    1.07
    叒
    1.07
     unexpectedly
    1.07
    Activations Density 0.185%

    No Known Activations