© 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. 13954
    Prev
    Next
    INDEX
    Explanations

    mia

    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
    திக
    2.72
     thoại
    2.65
    ্লা
    2.56
    না
    2.47
    缚
    2.44
    rer
    2.39
     fēng
    2.38
    犮
    2.36
    ワク
    2.33
    send
    2.33
    POSITIVE LOGITS
    ations
    2.49
    ktional
    2.37
    ating
    2.34
    лете
    2.34
     обстоя
    2.31
    ভিতে
    2.27
    ienti
    2.26
    ativer
    2.22
    ificantly
    2.19
    izlik
    2.19
    Activations Density 0.027%

    No Known Activations