© 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. 73073
    Prev
    Next
    INDEX
    Explanations

    is/are/has followed by descriptor

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

    non-negative quantities

    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
    ्ड
    0.50
    率先
    0.49
     متعلقه
    0.48
     الاخر
    0.47
     wallpapers
    0.47
    t
    0.46
     नवम्बर
    0.44
     दैट
    0.44
     العق
    0.43
     الجرس
    0.43
    POSITIVE LOGITS
     い
    0.47
     đạo
    0.46
     mujer
    0.46
     coppia
    0.46
    ся
    0.44
    শিয়া
    0.44
    husband
    0.43
    丈夫
    0.43
     gọi
    0.43
    Tai
    0.42
    Activations Density 0.000%

    No Known Activations