© 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. 455
    Prev
    Next
    INDEX
    Explanations

    3%

    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
    ह
    0.99
    り
    0.91
    いた
    0.89
    부터
    0.87
    ول
    0.87
    ס
    0.82
    ра
    0.79
    𝓲
    0.79
    𝑵
    0.79
    ી
    0.77
    POSITIVE LOGITS
    是非常
    0.80
    ️⃣
    0.72
     valeurs
    0.70
    ó
    0.70
     défaut
    0.69
     générations
    0.68
     vezes
    0.67
     Prüfung
    0.67
     yra
    0.66
     implique
    0.66
    Activations Density 0.826%

    No Known Activations