© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 1383
    Prev
    Next
    INDEX
    Explanations

    Return on Equity (ROE)

    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
    लीफ
    1.56
    प्पी
    1.48
    िप्स
    1.45
    Saund
    1.44
    Determination
    1.42
    া
    1.41
    जिंग
    1.41
     format
    1.40
     determination
    1.40
    checksum
    1.39
    POSITIVE LOGITS
    臃
    1.59
    ゙
    1.50
    anesu
    1.50
    ડે
    1.49
    力的
    1.49
     dioxane
    1.48
    romb
    1.48
    }_{\
    1.47
    irteenth
    1.47
    住宿
    1.47
    Activations Density 0.024%

    No Known Activations