© 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. 10109
    Prev
    Next
    INDEX
    Explanations

    methods, vector, Master, silence, ka

    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
    econ
    1.36
    idin
    1.35
    comps
    1.34
    י
    1.33
    沿
    1.28
    ktiv
    1.26
    ați
    1.26
    appan
    1.26
    textColor
    1.25
     ри
    1.24
    POSITIVE LOGITS
     scooped
    1.23
     COUNCIL
    1.20
     Controller
    1.20
    =:
    1.18
     opérateurs
    1.18
     exceeds
    1.16
    燈
    1.14
     Controllers
    1.14
    ഠ
    1.13
    서는
    1.13
    Activations Density 0.000%

    No Known Activations