© 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. 228497
    Prev
    Next
    INDEX
    Explanations

    contact information

    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
     lũ
    0.51
     kênh
    0.50
    sparsity
    0.50
    rzez
    0.50
     城
    0.48
    Ⲉ
    0.48
    apro
    0.47
    ய்ட
    0.47
    OAc
    0.46
     രീതി
    0.46
    POSITIVE LOGITS
     uniformed
    0.48
     Defense
    0.46
     telephones
    0.45
     Recovery
    0.41
     World
    0.41
     Institute
    0.41
    祝
    0.40
     Husky
    0.40
     Photographic
    0.40
    嬂
    0.39
    Activations Density 0.001%

    No Known Activations