© 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. 7161
    Prev
    Next
    INDEX
    Explanations

    specific classifications

    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
    และ
    0.65
    પણે
    0.62
    J
    0.60
    বড়
    0.59
    O
    0.57
    ých
    0.57
    過程中
    0.56
    Мо
    0.56
    新的
    0.55
     Я
    0.54
    POSITIVE LOGITS
     undeniably
    0.65
     solely
    0.64
     everyone
    0.64
     overly
    0.63
     merely
    0.62
     commonplace
    0.60
     accustomed
    0.60
     excessively
    0.60
     hijacking
    0.60
     hijacked
    0.59
    Activations Density 0.001%

    No Known Activations