© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 9399
    Prev
    Next
    INDEX
    Explanations

    sending out

    np_acts-logits-general · gemini-2.5-flash-lite

    dispatching items or information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soluble
    0.58
    akty
    0.57
    ać
    0.54
    ak
    0.51
    า
    0.50
    ace
    0.50
    unkte
    0.49
    鹸
    0.48
    ure
    0.47
     skóry
    0.47
    POSITIVE LOGITS
     send
    1.18
     보내
    1.17
     भेज
    1.16
     sending
    1.15
     Sending
    1.15
    Sending
    1.13
     посы
    1.13
     gönder
    1.10
     gönd
    1.10
     भेजा
    1.09
    Activations Density 0.085%

    No Known Activations