© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 62521
    Prev
    Next
    INDEX
    Explanations

    explaining issues or concepts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     세포
    0.45
    细胞
    0.44
    苷
    0.41
    øy
    0.40
     cellulaire
    0.40
    系统
    0.39
    完毕
    0.39
    是一种
    0.39
     comprenant
    0.39
    5
    0.39
    POSITIVE LOGITS
     headwinds
    0.58
     showrooms
    0.50
     финанси
    0.50
     onslaught
    0.48
     ambitions
    0.47
     underdog
    0.47
     mercantil
    0.46
     behest
    0.46
     injustice
    0.46
     onus
    0.46
    Activations Density 0.014%

    No Known Activations