© 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. 10575
    Prev
    Next
    INDEX
    Explanations

    cook for or until

    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
     회
    1.40
     कार्यकारी
    1.37
    으로부터
    1.34
     행
    1.32
     հատ
    1.32
     đảo
    1.30
    UKI
    1.30
    ද්
    1.27
    culis
    1.25
    ⺀
    1.24
    POSITIVE LOGITS
     allot
    1.32
    ingt
    1.11
    ingin
    1.05
     ano
    1.03
    ing
    1.00
    рите
    0.99
    ingu
    0.97
    ოგ
    0.95
    ear
    0.95
    ilah
    0.95
    Activations Density 0.131%

    No Known Activations