© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5647
    Prev
    Next
    INDEX
    Explanations

    you need

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     সৃষ্ট
    0.78
    အရ
    0.72
     wished
    0.69
     hadn
    0.67
    แก้ไข
    0.67
    쁜
    0.66
    स्वर
    0.66
     _)
    0.65
     ऑस्ट्रेलियाई
    0.64
     HAD
    0.64
    POSITIVE LOGITS
    මාණය
    0.66
     Care
    0.65
     Afternoon
    0.65
    جهزة
    0.64
     Pared
    0.62
    ան
    0.62
     chlorine
    0.62
     کورٹ
    0.61
     Chlorine
    0.61
     Sonne
    0.61
    Activations Density 0.086%

    No Known Activations