© 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. 10562
    Prev
    Next
    INDEX
    Explanations

    do you want/have

    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
     strategies
    0.89
     particular
    0.89
     schemes
    0.88
     techniques
    0.87
     It
    0.87
     There
    0.85
     プ
    0.85
    г
    0.83
     부분을
    0.82
     methods
    0.81
    POSITIVE LOGITS
     مول
    1.12
    Oui
    1.09
    wanath
    1.07
     YES
    1.06
    áb
    1.03
    BELL
    1.03
    Yes
    1.02
     Nein
    1.01
     Bóng
    1.00
    ubercul
    0.99
    Activations Density 0.139%

    No Known Activations