© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 15474
    Prev
    Next
    INDEX
    Explanations

    subscribe, listen, notifications, events

    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
     pharmacokinetic
    0.44
    thisStudent
    0.43
     బంగ
    0.42
    מח
    0.42
     изделия
    0.42
    បែ
    0.42
    滉
    0.42
    礡
    0.42
     подо
    0.41
     பிரமி
    0.41
    POSITIVE LOGITS
     notifications
    0.91
     notification
    0.90
     Notifications
    0.87
     Notification
    0.86
    事件
    0.82
     subscriptions
    0.82
    通知
    0.79
    Notification
    0.78
     subscribed
    0.78
    监听
    0.78
    Activations Density 0.166%

    No Known Activations