© 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. 6051
    Prev
    Next
    INDEX
    Explanations

    options and features

    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
     lágrimas
    1.30
    Dots
    1.20
     দৃষ্টিভ
    1.20
    Scripts
    1.20
    ртов
    1.14
    хо
    1.11
     critères
    1.09
    签
    1.08
    Гц
    1.07
     únicas
    1.06
    POSITIVE LOGITS
     roasted
    1.28
     blasted
    1.27
     blasting
    1.22
     myeloid
    1.20
     slams
    1.19
     nautical
    1.18
    批评
    1.18
     nan
    1.18
     velv
    1.18
     roasting
    1.17
    Activations Density 0.000%

    No Known Activations