© 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. 11460
    Prev
    Next
    INDEX
    Explanations

    contrastive conjunctions

    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
    ͆
    0.80
     berühm
    0.79
    ᴛ
    0.77
    ♡
    0.73
    ᴍ
    0.70
     también
    0.69
     humains
    0.69
     thrilling
    0.69
     🔥
    0.68
     ❤️
    0.66
    POSITIVE LOGITS
    但是
    1.10
    であるが
    0.98
     ancak
    0.91
    लेकिन
    0.90
    仅仅
    0.86
    ที่จะ
    0.86
     ಆದರೆ
    0.84
    或者是
    0.84
    आव
    0.83
    がありますが
    0.81
    Activations Density 0.231%

    No Known Activations