© 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. 65754
    Prev
    Next
    INDEX
    Explanations

    noun/verb followed by article/pronoun

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

    conditional statements and explanations

    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
    ;
    0.44
     ч
    0.43
     tremendous
    0.43
     intrigue
    0.42
     عمل
    0.42
     रैंक
    0.41
     चुनौ
    0.40
     deliver
    0.40
    เปลี่ยนแปลง
    0.40
     प्रौद्योगिकी
    0.40
    POSITIVE LOGITS
     તમારે
    0.52
     ক্ষয়ক্ষতি
    0.47
    aporation
    0.46
    误差
    0.45
    <unused2116>
    0.45
     olas
    0.45
     río
    0.44
    ່າງ
    0.44
     shoreline
    0.44
     dinding
    0.44
    Activations Density 0.000%

    No Known Activations