© 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. 228111
    Prev
    Next
    INDEX
    Explanations

    next Thursday, six hours, oftentimes impacts

    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
     उपा
    0.48
     occupation
    0.45
     hospitalized
    0.44
    ちゃん
    0.44
    푼
    0.44
    <0x0D>
    0.43
    ocin
    0.43
    ukar
    0.43
    sos
    0.43
     детства
    0.43
    POSITIVE LOGITS
    允许
    0.50
    দোষ
    0.49
    搛
    0.47
    renerg
    0.47
    
    0.46
    翕
    0.44
    实践
    0.44
    entwick
    0.44
    演讲
    0.44
    Wes
    0.44
    Activations Density 0.001%

    No Known Activations