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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 217
    Prev
    Next
    INDEX
    Explanations

    Python module imports

    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
     in
    1.05
     an
    1.02
     trud
    1.01
    ,
    0.99
     for
    0.95
     ignoring
    0.92
     fur
    0.92
     “
    0.90
     (
    0.90
     to
    0.88
    POSITIVE LOGITS
     Pengembangan
    1.95
     strutture
    1.87
     véhicules
    1.86
     pemilihan
    1.85
     Jenis
    1.85
     lingkungan
    1.84
     kendaraan
    1.83
     modèles
    1.82
     proprietà
    1.79
     gerenci
    1.77
    Activations Density 0.101%

    No Known Activations