© 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-262K
    7. 226664
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
     недвижи
    0.49
    Income
    0.43
     yüzde
    0.43
     Их
    0.43
    亳
    0.42
     nahezu
    0.41
    ewhere
    0.41
     Саме
    0.41
     Herpes
    0.40
     மட்டும்
    0.40
    POSITIVE LOGITS
    duplicates
    0.47
    社會
    0.45
    ਹਿ
    0.45
    बारी
    0.44
     नेपाली
    0.44
    সো
    0.43
     scottish
    0.43
     Paragu
    0.42
    鰱
    0.42
    ujú
    0.41
    Activations Density 0.007%

    No Known Activations