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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 310
    Prev
    Next
    INDEX
    Explanations

    Python function signatures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    了一
    1.10
    ї
    1.00
    quoi
    1.00
    jší
    0.97
     ureth
    0.94
    ****************
    0.89
    了一条
    0.87
    খান
    0.86
    了一個
    0.86
     platelets
    0.84
    POSITIVE LOGITS
    es
    2.10
    ت
    2.00
    k
    1.94
    이
    1.86
    ০
    1.82
    د
    1.78
    i
    1.78
    ת
    1.78
    ی
    1.77
    م
    1.73
    Activations Density 1.562%

    No Known Activations