© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10514
    Prev
    Next
    INDEX
    Explanations

    code structure and metadata

    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_22_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
    а
    0.62
     Fish
    0.61
    ig
    0.59
     Broadcast
    0.59
     a
    0.58
     Service
    0.58
     provided
    0.58
     kayb
    0.58
     and
    0.57
     claims
    0.57
    POSITIVE LOGITS
     douceur
    0.78
    ;?>
    0.77
     transnational
    0.77
     Pltf
    0.77
    
    0.76
    苌
    0.76
     mandib
    0.76
     amenazas
    0.75
     PLHIV
    0.74
    ஜ்மஹ
    0.74
    Activations Density 0.153%

    No Known Activations