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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 6707
    Prev
    Next
    INDEX
    Explanations

    website cookies and services

    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
     multidiscipl
    0.48
     nihil
    0.48
     ríg
    0.47
     discordant
    0.47
     romanzo
    0.46
    躯
    0.45
     aprob
    0.44
    
    0.43
     conflicted
    0.42
     verlieren
    0.42
    POSITIVE LOGITS
     services
    0.73
     서비스를
    0.66
     cookies
    0.66
     서비스
    0.60
     analytics
    0.59
     personalize
    0.59
     websites
    0.58
     website
    0.58
     transactions
    0.57
    services
    0.55
    Activations Density 0.147%

    No Known Activations