© 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. 7027
    Prev
    Next
    INDEX
    Explanations

    never happened

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

    principles and guidelines

    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
     水
    0.61
     artery
    0.59
     capacitors
    0.56
     walkway
    0.54
     oxide
    0.54
     JAVA
    0.53
     manganese
    0.53
     anthracite
    0.53
       
    0.52
     mangrove
    0.52
    POSITIVE LOGITS
     cynical
    0.65
    讽
    0.63
     rhet
    0.61
     ด่า
    0.61
    讥
    0.60
     cynicism
    0.59
    承认
    0.59
    삶
    0.59
    骂
    0.59
    惴
    0.59
    Activations Density 0.283%

    No Known Activations