© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8606
    Prev
    Next
    INDEX
    Explanations

    moods, attitudes, and atmosphere

    np_acts-logits-general · gemini-2.5-flash-lite

    vibe check

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    menu
    0.42
    们的
    0.41
    erna
    0.41
     منظر
    0.40
    vast
    0.38
     සම්බන්ධ
    0.38
    いたり
    0.38
    絆
    0.37
    किस
    0.37
    made
    0.37
    POSITIVE LOGITS
     perv
    0.79
     permeates
    0.77
     conducive
    0.76
     permeated
    0.75
     prevailing
    0.74
     perme
    0.71
     conveyed
    0.69
     prevails
    0.68
     shifts
    0.67
    营造
    0.65
    Activations Density 0.058%

    No Known Activations