© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 11756
    Prev
    Next
    INDEX
    Explanations

    Usage: $0

    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_13_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
    ដ្ឋាន
    1.14
     kültür
    1.10
     문화
    1.09
    成品
    1.07
    砜
    1.06
    퀸
    1.06
    larghezza
    1.03
     fyrir
    1.03
     संस्कृति
    1.02
     فرهنگ
    1.01
    POSITIVE LOGITS
     Plus
    0.92
     তুই
    0.90
     helping
    0.87
     doing
    0.84
     announcing
    0.83
     +
    0.82
     which
    0.80
     plus
    0.79
     alone
    0.79
     Hernández
    0.78
    Activations Density 0.038%

    No Known Activations