© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6786
    Prev
    Next
    INDEX
    Explanations

    items in a list

    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_31_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
     having
    1.35
     HAVING
    1.14
     Having
    1.11
    having
    1.09
    Having
    1.05
    有
    1.00
     ayant
    0.98
    มี
    0.95
     имели
    0.93
     teniendo
    0.89
    POSITIVE LOGITS
     available
    0.68
    available
    0.66
     marcado
    0.64
     associated
    0.63
    which
    0.61
     които
    0.60
    嗎
    0.60
     which
    0.57
     พวก
    0.56
     উৎপ
    0.55
    Activations Density 0.272%

    No Known Activations