© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6386
    Prev
    Next
    INDEX
    Explanations

    demand that or have

    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
     restarts
    0.57
     න
    0.52
     rnorm
    0.52
    DistanceFrom
    0.52
     रिपीट
    0.52
    𝓱
    0.52
    ቀት
    0.51
    ╧
    0.50
    ွေ
    0.50
    ቴ
    0.49
    POSITIVE LOGITS
     exchange
    2.78
    交换
    2.53
     exchanged
    2.47
    exchange
    2.41
     exchanging
    2.41
     Exchange
    2.36
     swap
    2.34
     exchanges
    2.31
    交換
    2.31
    Exchange
    2.31
    Activations Density 0.303%

    No Known Activations