© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1045
    Prev
    Next
    INDEX
    Explanations

    *

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    เพียง
    0.94
    ्यारह
    0.86
     Skyscrapers
    0.83
    garakan
    0.82
     Zeitschr
    0.82
    hiddenMap
    0.82
     centrifuged
    0.81
    
    0.81
     condolences
    0.78
     deuter
    0.78
    POSITIVE LOGITS
    ar
    0.94
    aneous
    0.84
    ri
    0.83
    ro
    0.81
    ()=>{
    0.79
     riusc
    0.77
    ada
    0.76
    lers
    0.76
    om
    0.73
    و
    0.73
    Activations Density 3.673%

    No Known Activations