© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1134
    Prev
    Next
    INDEX
    Explanations

    Gemma, Netherlands

    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
    до
    0.64
    ду
    0.63
    最も
    0.59
     весь
    0.58
    ва
    0.53
     самый
    0.52
    з
    0.52
    🫤
    0.52
    ſed
    0.52
    та
    0.52
    POSITIVE LOGITS
     National
    0.88
     University
    0.82
     United
    0.82
     International
    0.79
     Institute
    0.79
     Museum
    0.79
     Institut
    0.77
     British
    0.72
     American
    0.72
     Smithsonian
    0.71
    Activations Density 0.122%

    No Known Activations