© 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. 13775
    Prev
    Next
    INDEX
    Explanations

    python programming constructs

    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
    tat
    1.86
    dle
    1.86
    dling
    1.86
    个
    1.80
    nake
    1.77
    ្ត
    1.72
    tta
    1.70
    ক্ট
    1.70
    dering
    1.67
    nrow
    1.65
    POSITIVE LOGITS
    Ե
    1.89
    лят
    1.85
    انه
    1.82
    𝒸
    1.80
    Υ
    1.80
    ANCES
    1.74
    掾
    1.74
    لاین
    1.71
    osyl
    1.70
    ğ
    1.70
    Activations Density 0.086%

    No Known Activations