© 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. 13486
    Prev
    Next
    INDEX
    Explanations

    over and over again

    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
    es
    1.58
    ed
    1.45
    pero
    1.45
    z
    1.42
    ie
    1.36
     Somers
    1.35
     activities
    1.34
    y
    1.33
    edd
    1.33
    emis
    1.32
    POSITIVE LOGITS
    ⺊
    2.04
    았던
    2.02
    았
    2.02
     দেখিতে
    1.98
     (".
    1.95
     ([[
    1.92
     行っ
    1.91
    楖
    1.91
     聞い
    1.90
    اءِ
    1.88
    Activations Density 0.001%

    No Known Activations