© 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
    2. Gemma-3-12B-IT
    3. 31-GEMMASCOPE-2-RES-16K
    4. 15049
    Prev
    Next
    INDEX
    Explanations

    explaining capabilities that feel almost futuristic. And the ripples of this breakthrough are already reaching That was six months ago. Six months ago, this would have been unthinkable. Now… now, I hold her hand as we walk down Main Street.Here's the explanation for the neuron's behavior:unexpectedly remarkable

    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
     veya
    0.89
     또는
    0.79
     주로
    0.75
     Preferably
    0.74
    が多い
    0.73
     generalmente
    0.73
     असल्यास
    0.73
     hoặc
    0.73
     terutama
    0.73
     szczególnie
    0.72
    POSITIVE LOGITS
    竟然
    1.73
     addirittura
    1.67
     (!)
    1.57
    居然
    1.53
    (!)
    1.53
    !!!!!
    1.43
    ?!?!
    1.41
    ?!
    1.39
    !!!
    1.38
     freaking
    1.37
    Activations Density 0.087%

    No Known Activations