© 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. 10543
    Prev
    Next
    INDEX
    Explanations

    svg markup

    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
     chair
    0.83
    stuffs
    0.81
    OWER
    0.79
     chassis
    0.76
    ሢ
    0.76
    ilty
    0.75
     চাইলে
    0.75
    ories
    0.74
    ㎢
    0.74
    тать
    0.74
    POSITIVE LOGITS
     Republike
    0.91
    gång
    0.84
     versie
    0.81
    ắp
    0.80
     republik
    0.79
    Acrylic
    0.78
    リュ
    0.78
     मंग
    0.77
    Unsupported
    0.76
    republik
    0.75
    Activations Density 0.003%

    No Known Activations