© 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. 15-GEMMASCOPE-2-RES-16K
    7. 4319
    Prev
    Next
    INDEX
    Explanations

    data and network operations

    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_15_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
    畿
    0.97
    thers
    0.91
    čo
    0.88
     incol
    0.87
    udeau
    0.86
     piedi
    0.85
    央
    0.83
     sopr
    0.82
    肇
    0.81
    зино
    0.80
    POSITIVE LOGITS
     Þ
    1.49
    出来
    1.42
    咸
    1.36
    出去
    1.35
    Chile
    1.35
    料
    1.33
    名称
    1.32
    Þ
    1.32
     бата
    1.31
     okul
    1.31
    Activations Density 0.096%

    No Known Activations