© 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. 13937
    Prev
    Next
    INDEX
    Explanations

    numbers and citations

    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
    𒄿
    1.27
     phon
    1.27
    améliorer
    1.24
     angustato
    1.22
     ē
    1.18
     assistive
    1.18
     divaricatis
    1.17
    𒁉
    1.16
    لر
    1.16
     anne
    1.15
    POSITIVE LOGITS
     Business
    1.09
     수
    1.09
     Math
    1.06
     (
    1.05
     Power
    1.01
     Economic
    0.97
     만
    0.96
     Maths
    0.95
     Sleep
    0.94
     Market
    0.92
    Activations Density 0.043%

    No Known Activations