© 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-262K
    7. 51601
    Prev
    Next
    INDEX
    Explanations

    identify core values, customers, desires

    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_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
    бле
    0.50
    逆
    0.50
     Тихо
    0.49
    У
    0.49
    وازي
    0.48
    ви
    0.48
    爸
    0.47
    清水
    0.47
    頭
    0.46
    娘
    0.45
    POSITIVE LOGITS
     Form
    0.47
     takeaways
    0.46
     AST
    0.45
    ،
    0.45
                
    0.44
     flavoured
    0.44
     က
    0.43
     adoption
    0.43
     handful
    0.43
     Cumm
    0.43
    Activations Density 0.006%

    No Known Activations