© 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. 10047
    Prev
    Next
    INDEX
    Explanations

    specified action or number

    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
    眩
    1.13
     борьбе
    1.06
     борьбы
    1.05
     Styling
    1.04
     styling
    1.03
     FOD
    1.02
     tipping
    1.01
     Į
    1.00
     въ
    0.99
    ᕼ
    0.97
    POSITIVE LOGITS
    using
    1.09
    ocally
    1.09
     sols
    1.04
     solemnly
    1.03
    alunos
    1.01
     USING
    0.97
     Cours
    0.97
    nucleus
    0.97
     using
    0.95
    Aula
    0.94
    Activations Density 0.233%

    No Known Activations