© 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. 7-GEMMASCOPE-2-RES-16K
    7. 14698
    Prev
    Next
    INDEX
    Explanations

    product traditions

    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_7_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
    앉
    2.02
     минуту
    1.75
    eynman
    1.75
    aço
    1.70
    睡觉
    1.70
    timers
    1.68
     бумаги
    1.68
     precautions
    1.66
    वार
    1.66
     ночь
    1.64
    POSITIVE LOGITS
    tains
    1.66
    ̃
    1.54
    rial
    1.49
    ̣
    1.49
    lical
    1.48
    textup
    1.48
    iera
    1.47
    𝗵
    1.47
    (";
    1.45
    rella
    1.43
    Activations Density 0.000%

    No Known Activations