© 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. 208850
    Prev
    Next
    INDEX
    Explanations

    long-term investments, Asian countries, led lighting, unarmed protesters

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

    health and technology concepts

    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
     determinada
    0.54
     ficar
    0.49
     ambassador
    0.48
    ו
    0.48
     ambassadors
    0.48
     chegar
    0.47
    छि
    0.47
     llegar
    0.47
     xưa
    0.47
     falam
    0.47
    POSITIVE LOGITS
    itling
    0.53
    etail
    0.50
    ü
    0.50
    的服务
    0.49
    ayon
    0.48
    ünün
    0.48
    face
    0.47
    无效
    0.47
    unin
    0.47
    ကုန်
    0.47
    Activations Density 0.001%

    No Known Activations