© 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. 7-GEMMASCOPE-2-RES-16K
    7. 10896
    Prev
    Next
    INDEX
    Explanations

    qualified healthcare professional

    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
    자
    1.69
    ieran
    1.62
    ön
    1.61
    iaire
    1.60
    자들이
    1.54
    ø
    1.54
    ræ
    1.53
    erd
    1.51
    agent
    1.51
    ö
    1.49
    POSITIVE LOGITS
     андроид
    2.59
     smartwatch
    2.45
     CDMA
    2.42
     Андроид
    2.37
     celular
    2.27
     Lollipop
    2.25
     Smartphone
    2.21
     celulares
    2.20
     aparelho
    2.16
    AudioManager
    2.16
    Activations Density 0.534%

    No Known Activations