© 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. 72260
    Prev
    Next
    INDEX
    Explanations

    UDP compared

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

    Transformer architecture and NLP

    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
    ม
    0.46
    ୭
    0.45
     Reduced
    0.44
    ת
    0.44
    תה
    0.42
     duis
    0.40
    ﻣ
    0.40
    tron
    0.39
    шается
    0.39
    Reduced
    0.39
    POSITIVE LOGITS
    ɨ
    0.47
     besondere
    0.44
     jüng
    0.43
    ப்பின
    0.42
     exuberant
    0.42
     enero
    0.42
    ancien
    0.41
     Katrina
    0.41
    പി
    0.41
     Özel
    0.41
    Activations Density 0.003%

    No Known Activations