© 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. 56599
    Prev
    Next
    INDEX
    Explanations

    distress, avoidance, and difficulties

    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
    ᆯ
    0.45
    并非
    0.45
    ᆸ
    0.44
    希少
    0.43
    歡迎
    0.41
    ቲክ
    0.40
    𝟭
    0.40
     rarest
    0.38
     spiaggia
    0.38
     pharmacies
    0.37
    POSITIVE LOGITS
     考え
    0.44
     wurden
    0.42
     Konz
    0.40
     wiederum
    0.40
     Mathematics
    0.39
     Math
    0.38
     Mathematical
    0.38
     pensamiento
    0.38
     Beide
    0.37
     Ł
    0.37
    Activations Density 0.020%

    No Known Activations