© 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. 57
    Prev
    Next
    INDEX
    Explanations

    good luck

    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
     посмотреть
    0.55
    勻
    0.54
    хать
    0.53
    냐면
    0.52
    这里
    0.52
    تقديم
    0.52
    ittaa
    0.51
    aih
    0.51
     Unterricht
    0.51
    こちら
    0.51
    POSITIVE LOGITS
     provides
    0.56
     svo
    0.54
    <eos>
    0.54
     नामक
    0.52
     dum
    0.51
     bien
    0.50
     smokers
    0.50
     disease
    0.50
     संघर्ष
    0.50
     esperanza
    0.49
    Activations Density 0.008%

    No Known Activations