© 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. 14877
    Prev
    Next
    INDEX
    Explanations

    do affirm actions

    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
    ">⁡</
    2.59
    𝒚
    2.56
     riti
    2.52
    empot
    2.52
    
    2.51
    ਆ
    2.50
    ☰
    2.50
    ᅭ
    2.42
    𝚍
    2.39
    鐪
    2.38
    POSITIVE LOGITS
    e
    3.03
    ی
    2.91
    د
    2.78
    ाना
    2.73
    에
    2.72
    an
    2.68
    i
    2.61
    ek
    2.55
    ੀ
    2.47
    nicy
    2.46
    Activations Density 0.004%

    No Known Activations