© 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. 163620
    Prev
    Next
    INDEX
    Explanations

    legal and social context

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

    setting and worldbuilding

    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
    än
    0.45
     মাথ
    0.44
    ्रीम
    0.44
    ية
    0.44
    ہ
    0.43
     ار
    0.42
    他的
    0.42
     হাসপাত
    0.42
    follow
    0.42
     انا
    0.41
    POSITIVE LOGITS
    워크
    0.46
     précisément
    0.46
    ACKNOWLEDGMENTS
    0.46
    WiFi
    0.45
    ouer
    0.45
    ర్చు
    0.45
    绪
    0.45
    wegen
    0.44
     이게
    0.44
    로우
    0.44
    Activations Density 0.000%

    No Known Activations