© 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-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 6598
    Prev
    Next
    INDEX
    Explanations

    code logic or instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_12_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
     Huntsville
    1.68
     taxpayers
    1.68
     conservatives
    1.67
    柏
    1.66
     kcal
    1.66
    headlines
    1.66
     Kild
    1.65
     tornadoes
    1.61
     tyd
    1.59
    :-)
    1.59
    POSITIVE LOGITS
     attendant
    0.99
    简称
    0.96
    oucher
    0.94
    ซีน
    0.86
    uale
    0.82
    ابي
    0.82
    спек
    0.82
     étrangères
    0.79
    uali
    0.79
    逅
    0.78
    Activations Density 0.021%

    No Known Activations