© 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. 15110
    Prev
    Next
    INDEX
    Explanations

    gradient descent, training, learning

    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
    Transit
    0.55
     แปล
    0.54
    hull
    0.53
    訳
    0.53
     secrecy
    0.52
     Raid
    0.52
    씰
    0.52
    president
    0.51
    来店
    0.51
    篾
    0.50
    POSITIVE LOGITS
     gradients
    1.22
     learning
    1.20
     gradient
    1.17
     Gradient
    1.16
     Learning
    1.11
     training
    1.09
    Learning
    1.07
    梯度
    1.06
    Gradient
    1.05
     навчання
    1.05
    Activations Density 0.423%

    No Known Activations