© 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. 218615
    Prev
    Next
    INDEX
    Explanations

    trademarks, responsible, professional, favorite

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

    enslaved labor and students

    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
    ipro
    0.51
    web
    0.47
    write
    0.47
    Web
    0.47
    9
    0.45
    RS
    0.45
    نوع
    0.45
    dub
    0.43
    iche
    0.43
    itre
    0.43
    POSITIVE LOGITS
     sacerd
    0.50
     Phal
    0.50
     altın
    0.49
     bağlı
    0.48
     volna
    0.48
     Đế
    0.48
     Änderungen
    0.48
    ၊
    0.48
     Manner
    0.46
     yǔ
    0.46
    Activations Density 0.000%

    No Known Activations