© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 14656
    Prev
    Next
    INDEX
    Explanations

    multi, multiplex, parallel, tracking, clusters, throughput

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

    multiple

    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_31_width_262k_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
     ಬಿ
    0.45
     دونوں
    0.43
     აღ
    0.40
     ಉತ್ಪನ್ನ
    0.40
     الفترة
    0.39
     जीवन
    0.39
    誢
    0.39
     ፈ
    0.39
     Гуляць
    0.38
    呤
    0.38
    POSITIVE LOGITS
     multiple
    0.79
     multiplex
    0.78
     multi
    0.71
     Multiple
    0.71
    Multiple
    0.70
     تعدد
    0.68
     multip
    0.67
     Multi
    0.67
     multiplayer
    0.66
    multiple
    0.65
    Activations Density 0.064%

    No Known Activations