© 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. 241941
    Prev
    Next
    INDEX
    Explanations

    legal and professional roles

    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
    ك
    0.55
    单
    0.48
    德国
    0.47
    认真
    0.47
    ف
    0.46
    自定义
    0.46
    德國
    0.46
    يمة
    0.45
    界
    0.45
    ка
    0.45
    POSITIVE LOGITS
     wodurch
    0.56
     DPRD
    0.49
     inhomogeneities
    0.48
    мости
    0.48
     uğ
    0.48
    yana
    0.46
     .)
    0.46
     どれ
    0.46
     inciting
    0.45
     ওয়াস
    0.45
    Activations Density 0.000%

    No Known Activations