© 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. 13724
    Prev
    Next
    INDEX
    Explanations

    DDR Museum

    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
    ित
    2.49
     turn
    2.03
    ाई
    2.00
     falls
    1.99
    vert
    1.98
    ist
    1.93
     meet
    1.87
    ↵
    1.84
    дол
    1.82
    িত
    1.79
    POSITIVE LOGITS
    ouvoir
    3.37
    ನ್ನು
    3.30
    huri
    2.99
    TextAppearance
    2.98
    plicial
    2.92
    ぇ
    2.87
    ComponentName
    2.86
    的对象
    2.81
    lehem
    2.81
    phalodes
    2.79
    Activations Density 0.037%

    No Known Activations