© 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. 181599
    Prev
    Next
    INDEX
    Explanations

    actions and status updates

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

    merges and between

    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
    舴
    0.48
     otomatis
    0.48
    瑢
    0.47
     ٹرسٹ
    0.47
     प्रयोग
    0.47
    阌
    0.47
     bhavanti
    0.45
    敔
    0.44
     menggunakan
    0.44
     बजे
    0.44
    POSITIVE LOGITS
     schwarz
    0.54
     shelved
    0.50
     flushed
    0.48
     deutsch
    0.48
     deutscher
    0.47
     haired
    0.46
     curriculum
    0.45
     dron
    0.44
    sampled
    0.44
     steeped
    0.44
    Activations Density 0.001%

    No Known Activations