© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 73078
    Prev
    Next
    INDEX
    Explanations

    other people's states or wishes

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

    passionate feelings and relationships

    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
    ব্যাপী
    0.45
    ոլ
    0.44
    আপনার
    0.43
    প্রসঙ্গত
    0.43
     బాగా
    0.42
     paradigma
    0.41
    📰
    0.41
     প্রাধান্য
    0.41
    🗺
    0.40
    简约
    0.40
    POSITIVE LOGITS
    其他人
    0.45
     injured
    0.45
     घायल
    0.43
    addam
    0.42
     wished
    0.41
     others
    0.41
     wounded
    0.40
     posteriormente
    0.40
     আত্মার
    0.40
     অন্যরা
    0.40
    Activations Density 0.003%

    No Known Activations