© 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. 31-GEMMASCOPE-2-RES-65K
    7. 19764
    Prev
    Next
    INDEX
    Explanations

    so-called or named

    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_31_width_65k_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
     oppression
    0.38
    דיו
    0.35
    श्मीर
    0.34
    反対
    0.34
    ገኙ
    0.34
    ברו
    0.34
    ڄ
    0.33
    かけ
    0.32
    یشہ
    0.32
     persuasion
    0.31
    POSITIVE LOGITS
     sogenannten
    0.52
     sogen
    0.50
     denominado
    0.48
     sogenannte
    0.48
    ogenesis
    0.40
     denominada
    0.40
     της
    0.39
     headquartered
    0.39
     tzv
    0.39
     tzw
    0.39
    Activations Density 0.148%

    No Known Activations