© 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. 174093
    Prev
    Next
    INDEX
    Explanations

    business and legal context

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

    history lessons

    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
    Training
    0.55
    Own
    0.53
    Self
    0.47
    Trends
    0.47
    Pickup
    0.46
    Skills
    0.45
    Efficiency
    0.44
    鏻
    0.44
    Tips
    0.44
    Coral
    0.44
    POSITIVE LOGITS
     isim
    0.54
     combin
    0.52
     absorbers
    0.50
     mereka
    0.50
     හි
    0.48
     combinatorial
    0.47
     adlı
    0.46
     combina
    0.46
     ແມ່ນ
    0.46
     ima
    0.46
    Activations Density 0.000%

    No Known Activations