© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 4804
    Prev
    Next
    INDEX
    Explanations

    sending messages

    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_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    もら
    0.96
    ionante
    0.87
    е
    0.85
    ak
    0.84
    ate
    0.83
    ian
    0.83
    inin
    0.82
    am
    0.81
    ot
    0.80
    も
    0.79
    POSITIVE LOGITS
     sends
    1.18
     send
    1.13
     sending
    1.13
     отправ
    1.07
     zacz
    1.07
     senden
    1.05
     envoyé
    1.04
    发送
    1.02
     भेजने
    1.01
     gửi
    0.98
    Activations Density 0.081%

    No Known Activations