© 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. 12212
    Prev
    Next
    INDEX
    Explanations

    concept or context starter

    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
    additional
    1.07
     additional
    1.04
     unlimited
    0.99
    ej
    0.98
    urup
    0.95
     Also
    0.95
    Â
    0.95
     Motions
    0.90
    uco
    0.89
     limitless
    0.89
    POSITIVE LOGITS
    ➴
    1.40
     กี้
    1.36
     อืม
    1.34
     Angriff
    1.32
    🌘
    1.29
     Kobe
    1.28
    🌕
    1.28
     исполни
    1.27
    Narr
    1.26
     Husk
    1.26
    Activations Density 0.000%

    No Known Activations