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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1855
    Prev
    Next
    INDEX
    Explanations

    dotnet new console or webapi

    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
     Does
    0.94
    h
    0.90
    is
    0.89
     Nas
    0.89
     While
    0.88
     harass
    0.86
     From
    0.86
     Not
    0.85
     Nope
    0.84
     valable
    0.84
    POSITIVE LOGITS
     жи
    0.84
     нео
    0.81
    劻
    0.81
    addassa
    0.80
    кої
    0.79
     distinta
    0.78
    larının
    0.77
     miếng
    0.77
     condenser
    0.77
     kapat
    0.77
    Activations Density 0.002%

    No Known Activations