© 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. 15520
    Prev
    Next
    INDEX
    Explanations

    crying and sweating

    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
    ēl
    0.55
    洱
    0.53
     радиа
    0.52
     dissonance
    0.51
     収納
    0.50
     پوس
    0.50
    热闹
    0.50
     प्रतियोगिता
    0.50
    辐
    0.50
    博物
    0.49
    POSITIVE LOGITS
     tears
    1.89
     Tears
    1.77
     lágrimas
    1.66
     tear
    1.55
    泪
    1.53
    涙
    1.45
    淚
    1.39
     sweat
    1.36
     Tear
    1.35
     आंसू
    1.24
    Activations Density 0.158%

    No Known Activations