© 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. 112428
    Prev
    Next
    INDEX
    Explanations

    valuable resources

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

    buildings and infrastructure

    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
    Freeman
    0.49
    s
    0.46
     Freeman
    0.46
    inya
    0.46
    wan
    0.45
    ил
    0.44
     Gandhi
    0.43
     Совет
    0.43
    ih
    0.42
    oth
    0.42
    POSITIVE LOGITS
     ಆಗ
    0.53
     functionalities
    0.50
     DLC
    0.49
     driven
    0.49
    ╅
    0.49
    なし
    0.49
     λειτουργ
    0.48
    kiewicz
    0.48
     criticized
    0.48
     postponing
    0.47
    Activations Density 0.000%

    No Known Activations