© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 5796
    Prev
    Next
    INDEX
    Explanations

    distort patterns, improve texture, detect deception

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    瀟
    0.50
    naeus
    0.48
    counterx
    0.47
    stopwords
    0.46
     aidant
    0.46
     postdoctoral
    0.45
     جین
    0.45
     gastronomy
    0.45
    dinner
    0.44
     antidepressants
    0.44
    POSITIVE LOGITS
    扞
    0.46
    砻
    0.44
     디
    0.42
     Ağ
    0.42
     Diff
    0.42
     의미
    0.42
    Ⲟ
    0.42
     EPC
    0.41
    CMP
    0.41
     ı
    0.41
    Activations Density 0.012%

    No Known Activations