© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113165
    Prev
    Next
    INDEX
    Explanations

    people and professions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     เรา
    -1.36
     about
    -1.26
     geralmente
    -1.19
    のですが
    -1.16
     tudi
    -1.15
    onHide
    -1.15
     Acest
    -1.14
     également
    -1.14
     باشیم
    -1.13
     גם
    -1.13
    POSITIVE LOGITS
     who
    1.97
     will
    1.35
    <tr>
    1.23
     niyang
    1.19
     نمی
    1.19
    是谁
    1.15
    ച
    1.13
    ampilkan
    1.13
    ofing
    1.11
     quien
    1.10
    Activations Density 0.332%

    No Known Activations