© 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. 376
    Prev
    Next
    INDEX
    Explanations

    **mid-August and late October**

    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
    k
    0.94
    cC
    0.91
    ため
    0.90
    kus
    0.90
    positivo
    0.89
    OR
    0.87
     இன்ற
    0.86
    ler
    0.86
    m
    0.86
    culares
    0.86
    POSITIVE LOGITS
     marriages
    0.86
    ocardial
    0.83
     cancers
    0.79
    ಮನ
    0.77
     timpul
    0.76
     quarterbacks
    0.76
     Diabetic
    0.76
     drinker
    0.76
    umbles
    0.73
    肿瘤
    0.72
    Activations Density 0.000%

    No Known Activations