© 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. 10799
    Prev
    Next
    INDEX
    Explanations

    educational purposes only

    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
    冨
    1.26
    焓
    1.15
    ື່ອ
    1.14
     Бо
    1.09
     Фон
    1.07
    Flood
    1.05
    Со
    1.04
     力
    1.04
    脍
    1.03
    선을
    1.03
    POSITIVE LOGITS
     other
    1.17
     others
    1.16
     unspecified
    1.10
     miscellaneous
    1.09
     categories
    1.06
     outras
    1.05
     Others
    1.05
    Others
    1.02
     autres
    1.01
     इतर
    1.00
    Activations Density 0.032%

    No Known Activations