© 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-3-12B
    5. 12-GEMMASCOPE-2-RES-16K
    7. 365
    Prev
    Next
    INDEX
    Explanations

    ranking specific countries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_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
     hotspots
    0.91
    (
    0.80
    omy
    0.79
     ResponseEntity
    0.78
    ough
    0.77
    時の
    0.76
     చెందిన
    0.75
    raft
    0.74
    તમ
    0.74
     entity
    0.74
    POSITIVE LOGITS
    pedido
    0.90
     hemicontinuous
    0.89
    یہ
    0.88
     licking
    0.88
     pressione
    0.84
    מ
    0.84
     Bahkan
    0.84
    एचओ
    0.83
    𝐚
    0.83
    Какой
    0.82
    Activations Density 0.000%

    No Known Activations