© 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. 781
    Prev
    Next
    INDEX
    Explanations

    over phrases

    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
    elecimento
    2.93
     Crystallogr
    2.79
    ʣ
    2.65
    woorden
    2.59
    ussel
    2.58
    ลอด
    2.56
    acé
    2.56
    व्र
    2.55
     Cio
    2.54
    തിയ
    2.54
    POSITIVE LOGITS
    ्र
    2.57
     hinaus
    2.54
    不及
    2.51
    ্ক
    2.48
    blown
    2.39
    working
    2.33
    story
    2.15
    ⁢</
    2.10
    сть
    2.10
    𝒍
    2.09
    Activations Density 0.498%

    No Known Activations