© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 12822
    Prev
    Next
    INDEX
    Explanations

    battlethetitlepositionprocwrongthe

    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_24_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
    ed
    1.01
    d
    0.88
    o
    0.84
    c
    0.79
     CDT
    0.77
    쏴
    0.75
    i
    0.75
    cito
    0.71
     сопровожда
    0.71
     amply
    0.70
    POSITIVE LOGITS
     スーツ
    0.90
     ブル
    0.85
     być
    0.84
    اعر
    0.84
     budynku
    0.79
    กับ
    0.77
    به
    0.75
     Produk
    0.75
    ମ
    0.74
    sning
    0.74
    Activations Density 0.001%

    No Known Activations