© 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. 5347
    Prev
    Next
    INDEX
    Explanations

    repeated or continual actions

    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
    o
    0.47
    р
    0.45
    рт
    0.42
    oule
    0.42
     lengthened
    0.42
     Extra
    0.41
    вне
    0.41
    nikiem
    0.41
    ë
    0.40
     |
    0.40
    POSITIVE LOGITS
     successive
    1.08
     successively
    0.96
     repeatedly
    0.92
    何度も
    0.91
    不斷
    0.88
    不断的
    0.86
    不断
    0.82
     constantemente
    0.80
     successivement
    0.79
    繰り返
    0.78
    Activations Density 0.194%

    No Known Activations