© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 156
    Prev
    Next
    INDEX
    Explanations

    The AI neural network

    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
    Negative Logits
    。
    0.50
    を
    0.50
    을
    0.44
    和
    0.43
    とか
    0.42
            
    0.42
    ET
    0.41
    ”。
    0.41
    <0x0D>
    0.41
    の
    0.41
    POSITIVE LOGITS
    oretically
    0.78
     onus
    0.66
     impetus
    0.62
     inability
    0.61
     majority
    0.59
    odore
    0.58
     absence
    0.57
     meeste
    0.57
     outpouring
    0.56
     adage
    0.55
    Activations Density 0.568%

    No Known Activations