© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 8168
    Prev
    Next
    INDEX
    Explanations

    FBI, Obama, states, schools

    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_65k_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
    🥰
    1.60
    🥳
    1.58
     🥰
    1.55
    🤭
    1.52
    🫶
    1.46
    🤩
    1.45
    🤌
    1.35
     ✨
    1.34
     ২০২৩
    1.31
    🤤
    1.31
    POSITIVE LOGITS
     NASCAR
    1.83
     Obama
    1.74
     Michigan
    1.69
     Verizon
    1.62
     FBI
    1.62
     Florida
    1.61
     Illinois
    1.60
     California
    1.59
     Chicago
    1.59
     Obamacare
    1.58
    Activations Density 0.021%

    No Known Activations