© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 8630
    Prev
    Next
    INDEX
    Explanations

    potentially harmful or exploitative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_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
    rd
    0.89
    º
    0.89
    preferred
    0.81
    RD
    0.80
     rd
    0.79
    ˚
    0.78
     estate
    0.76
    paid
    0.76
    াবাদ
    0.76
     regulations
    0.75
    POSITIVE LOGITS
    <<(
    0.98
     <<
    0.91
    𝙀
    0.91
     sám
    0.87
     openai
    0.87
     dham
    0.86
     puedas
    0.86
    𝖊
    0.86
    र्टी
    0.86
    曳
    0.86
    Activations Density 0.037%

    No Known Activations