© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11722
    Prev
    Next
    INDEX
    Explanations

    federal agencies and sectors

    np_acts-logits-general · gemini-2.5-flash-lite

    AWS/GCP regions and accounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_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
    phs
    0.42
     પાર્
    0.39
     серьез
    0.38
    WithName
    0.38
     precept
    0.37
    ম্পতি
    0.37
     Attitudes
    0.36
     therefore
    0.36
    ﮈ
    0.36
     Swain
    0.36
    POSITIVE LOGITS
     Glory
    0.41
    純
    0.39
    geg
    0.39
    warna
    0.38
     Govt
    0.37
    ᅲ
    0.37
    рея
    0.37
    ionais
    0.37
    pure
    0.36
    lež
    0.36
    Activations Density 0.008%

    No Known Activations