© 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. 24-GEMMASCOPE-2-RES-16K
    7. 16074
    Prev
    Next
    INDEX
    Explanations

    sql, async, static

    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
    源
    0.84
    ホー
    0.80
    под
    0.76
    އ
    0.76
    ूंकि
    0.75
    োগ্রাফ
    0.75
    }-{
    0.74
    ተኛ
    0.73
    सब
    0.72
    bergh
    0.71
    POSITIVE LOGITS
     TypeScript
    0.80
     genie
    0.80
     Maths
    0.79
     Nautical
    0.78
     Ape
    0.76
     чы
    0.75
     வருகின்றனர்
    0.75
     ésta
    0.75
     rodzaj
    0.75
     éste
    0.74
    Activations Density 0.000%

    No Known Activations