© 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-65K
    7. 646
    Prev
    Next
    INDEX
    Explanations

    improvements and

    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_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
     inconclusive
    0.49
     terenie
    0.46
     culprit
    0.44
     కొంత
    0.41
    褻
    0.40
     неприят
    0.39
    ");*/
    0.38
    楧
    0.37
    ื่อง
    0.37
     curioso
    0.36
    POSITIVE LOGITS
     Improvements
    1.05
     improvements
    1.01
    Improvements
    0.96
     Verbesser
    0.93
     improved
    0.86
    Improved
    0.86
     amélior
    0.83
    改进
    0.83
     mejoras
    0.82
     verbeter
    0.82
    Activations Density 0.291%

    No Known Activations