© 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. 306
    Prev
    Next
    INDEX
    Explanations

    specific definitions or categories

    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
    دة
    1.50
    ्य
    1.39
    ب
    1.32
    ه
    1.27
    ių
    1.27
    دت
    1.23
    ا
    1.20
    رى
    1.19
    ال
    1.16
    ि
    1.13
    POSITIVE LOGITS
    ()=>{
    1.26
    ée
    1.20
     तरह
    1.16
    お待ち
    1.10
    热爱
    1.08
    υ
    1.01
    願い
    0.98
     publicized
    0.98
    েশন
    0.97
     handbag
    0.96
    Activations Density 0.108%

    No Known Activations