© 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. 5528
    Prev
    Next
    INDEX
    Explanations

    matte grey finishes

    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
     pavatt
    0.62
     unreliable
    0.61
    补偿
    0.56
    驴
    0.56
     governed
    0.55
    资格
    0.54
     nourrice
    0.54
     bookkeeping
    0.53
     stimulate
    0.52
     Physiology
    0.52
    POSITIVE LOGITS
     styling
    1.00
     exterior
    0.98
    Exterior
    0.97
    钣
    0.94
     grille
    0.93
    exterior
    0.91
     sleek
    0.90
     chrome
    0.90
     Styling
    0.87
    Chrome
    0.84
    Activations Density 0.270%

    No Known Activations