© 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. 1276
    Prev
    Next
    INDEX
    Explanations

    all of them

    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
     oder
    1.79
    或其他
    1.66
     eller
    1.63
     veya
    1.62
    （
    1.60
     или
    1.60
    india
    1.59
     atau
    1.57
     किंवा
    1.55
    ێک
    1.50
    POSITIVE LOGITS
    焓
    1.79
     그래
    1.71
     Brü
    1.68
    楦
    1.68
    ให้
    1.63
    ซิ
    1.61
     Zentr
    1.60
    瞳
    1.47
    ยังมี
    1.43
    เตอร์
    1.43
    Activations Density 0.746%

    No Known Activations