© 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. 122201
    Prev
    Next
    INDEX
    Explanations

    hardest job, favorite runs, breathing exercises

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

    breathing, performance, and protections

    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
     decom
    0.46
    in
    0.45
    contained
    0.44
     necessitated
    0.43
    ск
    0.43
    exe
    0.43
    з
    0.42
     McBride
    0.42
     agreeable
    0.42
    考え
    0.41
    POSITIVE LOGITS
    وفر
    0.50
    냅
    0.47
    ittää
    0.46
    你们
    0.46
    虚拟
    0.45
     drawed
    0.44
     अभिभाव
    0.43
    önes
    0.43
    创始
    0.43
    lllll
    0.42
    Activations Density 0.000%

    No Known Activations