© 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. 150
    Prev
    Next
    INDEX
    Explanations

    numbers after two

    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
    🔥🔥
    0.97
    いた
    0.97
    ছেন
    0.95
    न
    0.91
    ول
    0.89
    un
    0.86
    ל
    0.82
    ومن
    0.80
    ки
    0.80
    👉
    0.80
    POSITIVE LOGITS
    THING
    0.89
    tone
    0.84
    thirds
    0.80
    ️⃣
    0.77
    time
    0.73
     forego
    0.71
     puluh
    0.71
    0
    0.70
    ppled
    0.70
     Admit
    0.70
    Activations Density 0.553%

    No Known Activations