© 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. 208730
    Prev
    Next
    INDEX
    Explanations

    announcing weddings

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

    draft regulation, contact, romance, ST

    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
    匽
    0.48
     เรา
    0.47
    拯
    0.47
    при
    0.47
    ،
    0.46
    ，
    0.46
    пи
    0.45
     eing
    0.45
    価
    0.44
    Canvas
    0.44
    POSITIVE LOGITS
     separado
    0.50
     lluvias
    0.46
     কাছের
    0.46
     incluido
    0.46
     köy
    0.46
     Villages
    0.46
    Ẳ
    0.46
     ayrı
    0.45
     petani
    0.45
     wearables
    0.45
    Activations Density 0.000%

    No Known Activations