© 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. 225072
    Prev
    Next
    INDEX
    Explanations

    his personal

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

    counting down to holidays

    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
     kwamba
    0.48
     crédito
    0.47
     प्रशिक्
    0.42
     отсутствие
    0.42
     $>
    0.41
    )>\
    0.41
    <unused94>
    0.40
     Kyushu
    0.40
    によっては
    0.40
     स्टार्ट
    0.39
    POSITIVE LOGITS
    üy
    0.50
     Holidays
    0.50
     holidays
    0.49
    ном
    0.48
    皓
    0.47
    យើង
    0.46
    Conteudos
    0.46
    তাহাদের
    0.46
    我们将
    0.45
     ধারণ
    0.44
    Activations Density 0.000%

    No Known Activations