© 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. 219564
    Prev
    Next
    INDEX
    Explanations

    multilingual content

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

    exploring intimacy and healthy relationships

    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
    壟
    0.49
    ਘ
    0.49
    вни
    0.44
     बढ़त
    0.44
     долла
    0.43
    оте
    0.42
    및
    0.42
    ర్
    0.42
    гло
    0.42
    oxides
    0.41
    POSITIVE LOGITS
     mittlerweile
    0.47
    illary
    0.44
     speł
    0.44
     tatsächlich
    0.43
     delirium
    0.43
     सीड
    0.43
     véritable
    0.42
     ഒന്ന
    0.42
     beispielsweise
    0.41
     २०१
    0.40
    Activations Density 0.001%

    No Known Activations