© 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. 40-GEMMASCOPE-2-RES-16K
    7. 7770
    Prev
    Next
    INDEX
    Explanations

    rodents and mammals

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     jellyfish
    0.54
     ikan
    0.50
     sharks
    0.48
    魚
    0.48
     pter
    0.47
    鱼
    0.46
     растений
    0.46
     fish
    0.45
     Cattle
    0.45
     nitrogen
    0.45
    POSITIVE LOGITS
     rodent
    1.34
     mouse
    1.21
    🐭
    1.20
     rat
    1.16
    鼠
    1.16
     rodents
    1.16
    Mouse
    1.12
    mouse
    1.09
     Mouse
    1.05
    🐁
    1.03
    Activations Density 0.183%

    No Known Activations