© 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. 3164
    Prev
    Next
    INDEX
    Explanations

    importing code and buffers

    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
     курса
    1.05
     progn
    1.03
     курс
    1.02
    Scan
    1.00
    Funk
    1.00
    嗅
    1.00
     تضيفلها
    0.99
     LIFE
    0.99
    legs
    0.99
    Report
    0.99
    POSITIVE LOGITS
     plaster
    1.04
     Zayed
    1.04
    톈
    1.02
     gauze
    1.00
     Takeuchi
    0.99
    factory
    0.98
     Palestinian
    0.98
     Bale
    0.98
    kaf
    0.97
     photoc
    0.96
    Activations Density 0.014%

    No Known Activations