© 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. 65983
    Prev
    Next
    INDEX
    Explanations

    defense of, estate agents, for listening

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

    product or service costs

    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
    oloj
    0.49
    帜
    0.49
    ătur
    0.48
     могу
    0.46
    并通过
    0.45
    onite
    0.44
     хотите
    0.44
    优雅
    0.44
    amasını
    0.44
    larıyla
    0.43
    POSITIVE LOGITS
    辯
    0.47
     covid
    0.43
     bonding
    0.43
     traduit
    0.43
     balancing
    0.43
     infractions
    0.43
    幇
    0.43
    函數
    0.43
    銖
    0.42
     한다
    0.42
    Activations Density 0.001%

    No Known Activations