© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 31930
    Prev
    Next
    INDEX
    Explanations

    RO membrane separation

    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_262k_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
     furnaces
    0.40
     ಉತ್ಪನ್ನ
    0.40
    銷
    0.38
     कन
    0.38
    дна
    0.38
     قم
    0.37
     संलग्न
    0.37
     impurities
    0.37
     vente
    0.37
     Marlin
    0.37
    POSITIVE LOGITS
     membrane
    1.11
     Membrane
    1.01
     membranes
    1.00
     Membranes
    0.93
    membrane
    0.89
     мем
    0.88
     membr
    0.86
     membrana
    0.83
    膜
    0.83
     membran
    0.79
    Activations Density 0.007%

    No Known Activations