© 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. 13557
    Prev
    Next
    INDEX
    Explanations

    US laws and agencies

    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
    ي
    3.02
    лкой
    2.76
    всем
    2.69
    ЛЬ
    2.68
    لین
    2.62
    FromResult
    2.61
    roben
    2.60
    iracial
    2.56
    ССР
    2.55
    ა
    2.54
    POSITIVE LOGITS
    eket
    2.75
    𝘪
    2.64
    𝘦
    2.58
    𝗻
    2.55
     hoe
    2.53
    ゙
    2.46
    𝘴
    2.42
    𝘯
    2.42
    밀
    2.36
    ewarm
    2.33
    Activations Density 0.019%

    No Known Activations