© 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. 296
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     を
    0.38
    스를
    0.37
    を満
    0.34
     Abbiamo
    0.34
     높은
    0.34
     ጡ
    0.33
    事が
    0.32
    AlignedText
    0.32
    を
    0.32
     một
    0.32
    POSITIVE LOGITS
     size
    0.87
     location
    0.85
     characteristics
    0.84
     type
    0.84
     geography
    0.83
     types
    0.80
     style
    0.78
    类型
    0.78
     ধরন
    0.75
     styles
    0.74
    Activations Density 7.783%

    No Known Activations