© 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
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 9999
    Prev
    Next
    INDEX
    Explanations

    Earth and greenhouse effect

    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
     אַ
    1.42
     качества
    1.36
     tems
    1.34
     ๆ
    1.31
     符合
    1.29
    resión
    1.29
    CCESS
    1.28
     frivol
    1.27
     说明
    1.25
     нож
    1.25
    POSITIVE LOGITS
     duduk
    1.70
     Forbidden
    1.50
     budaya
    1.47
    બંધ
    1.43
    美国
    1.42
    लया
    1.40
     السعودية
    1.38
    áng
    1.37
    の
    1.35
    天空
    1.34
    Activations Density 0.000%

    No Known Activations