© 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-262K
    7. 244898
    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
    л
    0.48
    the
    0.44
    s
    0.43
    非
    0.42
    лат
    0.41
    u
    0.41
    ographystyle
    0.39
     বলেছেন
    0.39
    िफिशियल
    0.39
    lat
    0.39
    POSITIVE LOGITS
     också
    0.54
     ដ
    0.54
     البي
    0.53
     çoc
    0.53
     경로
    0.52
     erhö
    0.50
    Hö
    0.50
     Hered
    0.49
     verwendet
    0.48
     შეს
    0.48
    Activations Density 0.012%

    No Known Activations