© 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. 278
    Prev
    Next
    INDEX
    Explanations

    recipe, book, machine, symphony, handshake

    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
     અને
    0.55
     και
    0.54
     و
    0.52
    และ
    0.50
     ແລະ
    0.48
     également
    0.48
     ও
    0.46
     ايضا
    0.46
     மற்றும்
    0.46
     також
    0.46
    POSITIVE LOGITS
    般的
    0.72
     Shaped
    0.52
    ':
    0.49
    般
    0.49
     जिसमें
    0.48
    所有
    0.48
    like
    0.48
    裡的
    0.48
    型的
    0.47
     shaped
    0.47
    Activations Density 0.000%

    No Known Activations