© 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. 195754
    Prev
    Next
    INDEX
    Explanations

    social media, healing, leadership, music, business

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

    imagine stairs

    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
     UVA
    0.44
    化
    0.44
     Houd
    0.43
     tussen
    0.43
     NGOs
    0.42
     Hòa
    0.42
     took
    0.41
     hails
    0.41
     Peas
    0.41
    稀
    0.40
    POSITIVE LOGITS
    ası
    0.47
    ı
    0.46
    ۔
    0.46
     pedir
    0.46
    ıyorum
    0.46
    ті
    0.45
    тері
    0.45
    aisesti
    0.45
    ұ
    0.44
    Diagn
    0.44
    Activations Density 0.000%

    No Known Activations