© 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. 29119
    Prev
    Next
    INDEX
    Explanations

    pragmatics and discourse

    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
     kereszt
    0.39
     मूवी
    0.38
     डाउट
    0.38
    ジン
    0.38
    漢字
    0.37
     factorizar
    0.37
    ﻚ
    0.37
     spaz
    0.36
    ኋ
    0.36
    챔
    0.36
    POSITIVE LOGITS
     communicative
    0.96
     conversational
    0.76
     коммуника
    0.72
     communication
    0.71
     communic
    0.71
     socially
    0.70
     discourse
    0.68
     Communic
    0.66
     komunik
    0.64
     social
    0.64
    Activations Density 0.017%

    No Known Activations