© 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. 11672
    Prev
    Next
    INDEX
    Explanations

    webdriver initialization

    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
    hoi
    1.24
    rist
    1.24
    现在
    1.19
    我现在
    1.18
    rists
    1.16
    openc
    1.15
    hod
    1.15
    ٢
    1.15
    person
    1.15
    ٣
    1.13
    POSITIVE LOGITS
     반응
    1.24
    사와
    1.22
     端
    1.16
     요소
    1.10
     질
    1.06
     않았
    1.06
     化
    1.02
     컴퓨
    1.02
     reactants
    1.02
     COMPONENTS
    1.00
    Activations Density 0.011%

    No Known Activations