© 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. 220420
    Prev
    Next
    INDEX
    Explanations

    specialized foreign words

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

    how to build

    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
     sniffing
    0.45
     Yue
    0.45
     毛
    0.44
    夷
    0.44
     सुना
    0.43
     ชีวิต
    0.43
    ipro
    0.43
     எழுது
    0.42
     津
    0.42
     या
    0.42
    POSITIVE LOGITS
     fenó
    0.51
     verificación
    0.51
    स्टेबल
    0.50
    ওয়ার্ড
    0.49
    舩
    0.47
     ká
    0.46
    سترول
    0.46
     ionized
    0.45
     vás
    0.45
     vidrio
    0.45
    Activations Density 0.000%

    No Known Activations