© 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. 738
    Prev
    Next
    INDEX
    Explanations

    Mall

    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
    a
    2.11
    িমা
    2.10
    ਆਂ
    2.02
    ições
    2.01
    〝
    1.94
    ه
    1.94
    DownLatch
    1.93
    टावा
    1.91
     frictions
    1.88
     pertemuan
    1.87
    POSITIVE LOGITS
    imist
    2.41
    isti
    2.38
    𝗰
    2.21
    𝒾
    2.13
    ologist
    2.06
    cons
    1.99
    ismi
    1.99
    center
    1.96
    ist
    1.92
    idently
    1.90
    Activations Density 1.343%

    No Known Activations