© 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. 158626
    Prev
    Next
    INDEX
    Explanations

    fire pit, past clients, question that, an unethical

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

    improve performance and learning

    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
    अर्
    0.45
    diği
    0.44
    LOCATION
    0.43
     ettiği
    0.43
    。《
    0.42
    ถาน
    0.41
    禱
    0.41
    访问
    0.41
    ্তন
    0.41
    礼
    0.41
    POSITIVE LOGITS
     tôi
    0.49
     প্রক্রিয়াধীন
    0.49
     anderer
    0.47
     повинні
    0.47
     Tôi
    0.47
     يجب
    0.46
     कौशिक
    0.46
     esperti
    0.45
     ماہر
    0.44
    يديو
    0.44
    Activations Density 0.004%

    No Known Activations