© 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. 61330
    Prev
    Next
    INDEX
    Explanations

    specific word pairings

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

    risk allocation, you deserve

    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
     μία
    0.52
    ٹین
    0.51
    นี
    0.51
     İzmir
    0.50
    <unused54>
    0.48
     দ্রব
    0.48
     सरोवर
    0.48
     дево
    0.47
    uş
    0.47
     остается
    0.47
    POSITIVE LOGITS
    |^
    0.51
        
    0.50
    確か
    0.46
    dimensional
    0.46
    ‌
    0.45
     seventy
    0.44
     blood
    0.43
    #'
    0.43
    //!
    0.43
    ั่น
    0.43
    Activations Density 0.000%

    No Known Activations