© 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. 9326
    Prev
    Next
    INDEX
    Explanations

    believe

    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
     እን
    0.65
     मेह
    0.63
    довать
    0.60
    
    0.57
     которому
    0.53
    filesystem
    0.53
    Falling
    0.53
    𝓵
    0.52
    ევ
    0.52
    てもら
    0.52
    POSITIVE LOGITS
    marginal
    0.66
     marginal
    0.63
    nio
    0.59
     ){
    0.59
     শর্
    0.59
    expédition
    0.58
     variant
    0.57
     oznac
    0.57
     સમજ
    0.56
     NIKE
    0.55
    Activations Density 0.005%

    No Known Activations