© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9646
    Prev
    Next
    INDEX
    Explanations

    Google Cloud

    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
    审
    1.14
     подо
    1.14
     وا
    1.10
     yank
    1.07
     Jews
    1.07
     Киев
    1.06
     судь
    1.06
     Jew
    1.06
     욕
    1.05
     Ј
    1.03
    POSITIVE LOGITS
    isations
    1.04
    ised
    1.02
    isasi
    0.99
     diantaranya
    0.98
    چھ
    0.98
     utilised
    0.96
    isation
    0.94
     kebanyakan
    0.94
     essentiellement
    0.94
    giene
    0.93
    Activations Density 0.000%

    No Known Activations