© 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-262K
    7. 85096
    Prev
    Next
    INDEX
    Explanations

    communication and communicate

    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
     BUFFER
    0.38
    疊
    0.38
     buffer
    0.37
    стрии
    0.37
     गामा
    0.37
    析
    0.37
     Buffer
    0.36
    牫
    0.36
    KeyPressed
    0.36
    faulse
    0.36
    POSITIVE LOGITS
     communication
    2.59
    Communication
    2.41
    communication
    2.36
     comunicação
    2.31
     Communication
    2.30
     comunicación
    2.30
     komunik
    2.30
     komunikasi
    2.28
     communicate
    2.25
     comunicazione
    2.25
    Activations Density 0.110%

    No Known Activations