© 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. 40-GEMMASCOPE-2-RES-262K
    7. 166427
    Prev
    Next
    INDEX
    Explanations

    human trafficking hotline

    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_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
     реги
    0.43
    нан
    0.41
    кен
    0.41
    ürnberg
    0.41
    텝
    0.41
     глоба
    0.40
     темы
    0.39
    ട്ട്
    0.38
     международных
    0.38
    耿
    0.38
    POSITIVE LOGITS
     who
    0.42
     ισ
    0.42
    rossover
    0.41
     embracing
    0.40
     enjoying
    0.39
     الذي
    0.39
    issor
    0.38
    Who
    0.38
     go
    0.37
     acl
    0.36
    Activations Density 0.008%

    No Known Activations