© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 7232
    Prev
    Next
    INDEX
    Explanations

    sending information

    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_16k_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
    优雅
    0.43
     производи
    0.43
    Adjacent
    0.43
    ༔
    0.43
     автофо
    0.43
     அதாவது
    0.42
     μπ
    0.40
    ₂)
    0.40
     presento
    0.40
    શો
    0.39
    POSITIVE LOGITS
     sending
    0.95
     sends
    0.92
     send
    0.89
     gửi
    0.87
     envía
    0.82
     Sending
    0.80
     mengirim
    0.78
    发送
    0.75
    Sending
    0.75
    sending
    0.75
    Activations Density 0.290%

    No Known Activations