© 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. 199432
    Prev
    Next
    INDEX
    Explanations

    punctuation, foreign language, and efficiency

    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
    \
    0.44
     Тому
    0.42
    ti
    0.41
    )))
    0.40
    )
    0.40
    asts
    0.40
    indak
    0.40
     किंवा
    0.38
    ))
    0.38
    lll
    0.38
    POSITIVE LOGITS
     सबके
    0.50
    ोरेशन
    0.48
     puisque
    0.46
    ন্টি
    0.46
    রির
    0.46
    ρή
    0.46
    總
    0.46
     hubungan
    0.45
    ंबकीय
    0.45
     nhỏ
    0.45
    Activations Density 0.003%

    No Known Activations