© 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. 3518
    Prev
    Next
    INDEX
    Explanations

    translation and quantification

    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
     oops
    1.09
     zina
    1.08
     sorry
    1.05
    Stepper
    1.04
     hæ
    1.03
     sta
    1.02
    !--
    1.00
    !.
    0.99
     Sting
    0.99
     Echo
    0.99
    POSITIVE LOGITS
     entreprises
    1.29
    ைகளுக்கு
    1.28
     に対
    1.23
    ைகளும்
    1.22
     oluşan
    1.21
     предприятий
    1.20
    ைகள
    1.20
     እንዲሁም
    1.18
     femenina
    1.17
    cimientos
    1.17
    Activations Density 0.522%

    No Known Activations