© 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. 89214
    Prev
    Next
    INDEX
    Explanations

    javascript file size reduction

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

    programming concepts and keywords

    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
    偕
    0.44
    简约
    0.43
     aumentare
    0.41
     aumentado
    0.41
     aumentar
    0.40
     augmenter
    0.40
     применяется
    0.39
    SXml
    0.39
    ຖານ
    0.39
     kullanılır
    0.38
    POSITIVE LOGITS
     SON
    0.51
     l
    0.49
     FIL
    0.49
     PROJECT
    0.46
     anyone
    0.45
     POL
    0.45
    uh
    0.44
     sais
    0.44
     MOT
    0.43
     SHEET
    0.43
    Activations Density 0.000%

    No Known Activations