© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-16K
    7. 3221
    Prev
    Next
    INDEX
    Explanations

    repository, best practices, sum, odd, dinner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
    ֩
    0.73
     개의
    0.68
    |_{
    0.64
     의한
    0.63
    
    0.63
    மனித
    0.63
     による
    0.62
    #
    0.61
    ዚያ
    0.61
    <sub>
    0.61
    POSITIVE LOGITS
    AN
    0.62
    ان
    0.60
     assert
    0.58
    юра
    0.56
    यो
    0.55
    IN
    0.55
     metadata
    0.55
    metadata
    0.54
    ását
    0.54
    an
    0.54
    Activations Density 0.876%

    No Known Activations