© 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. 7815
    Prev
    Next
    INDEX
    Explanations

    css color and border properties

    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
     އި
    0.42
     род
    0.40
     الل
    0.37
     qil
    0.35
     हमसे
    0.34
    আরও
    0.34
     пошу
    0.34
     جست
    0.34
    ancı
    0.33
    ])+
    0.33
    POSITIVE LOGITS
    段階
    0.39
    眼
    0.38
    regnum
    0.37
    一群
    0.37
    ாளர்களுக்கு
    0.37
    一场
    0.37
     RSD
    0.36
    regression
    0.36
    Mock
    0.36
    Harold
    0.36
    Activations Density 0.025%

    No Known Activations