© 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. 7122
    Prev
    Next
    INDEX
    Explanations

    source destination

    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
     ত
    0.70
     υ
    0.66
     اكت
    0.62
     ஆனது
    0.62
    webkit
    0.61
     수도
    0.61
     cio
    0.60
     costa
    0.59
    şti
    0.58
    ｂ
    0.58
    POSITIVE LOGITS
    iye
    0.88
    Dollars
    0.83
     солнца
    0.80
     salir
    0.78
     Cual
    0.78
    ͓
    0.78
    ర్
    0.77
     Fuck
    0.76
     Absch
    0.75
     CHCl
    0.75
    Activations Density 0.000%

    No Known Activations