© 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. 116930
    Prev
    Next
    INDEX
    Explanations

    has

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

    academic performance calculations

    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
     avait
    0.46
     Nearest
    0.46
    軒
    0.45
     avaient
    0.45
     innego
    0.45
     destinés
    0.44
     Entities
    0.44
     karoti
    0.44
    を変更
    0.44
     গিয়েছিলেন
    0.44
    POSITIVE LOGITS
    
    0.47
    ప
    0.46
    *,
    0.46
    协
    0.45
    原始内容存档
    0.44
    科学
    0.44
    职工
    0.43
    致力于
    0.42
    lasm
    0.42
    欢迎
    0.42
    Activations Density 0.000%

    No Known Activations