© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1989
    Prev
    Next
    INDEX
    Explanations

    binary code representation

    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
     เป็น
    1.60
     و
    1.56
    ous
    1.56
    และ
    1.55
     ،
    1.55
    ،
    1.51
     وت
    1.49
    7
    1.48
    .
    1.47
    8
    1.44
    POSITIVE LOGITS
     Ủy
    1.99
    InstrumentedTest
    1.97
    യാൾ
    1.95
    ERVER
    1.88
     órgão
    1.88
     cursory
    1.78
     άνθρω
    1.77
     constaté
    1.75
     ủy
    1.75
    mousePressed
    1.72
    Activations Density 0.066%

    No Known Activations