© 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. 35141
    Prev
    Next
    INDEX
    Explanations

    part of my Hips

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

    work requiring understanding

    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
    開放
    0.49
    潑
    0.46
     respond
    0.44
    蓓
    0.44
     demonstrations
    0.42
     singleRun
    0.42
    ഞ്ഞു
    0.41
    分鐘
    0.41
    气氛
    0.41
    泼
    0.41
    POSITIVE LOGITS
    arlo
    0.47
     ло
    0.45
     הע
    0.43
    uck
    0.43
    어도
    0.43
    olio
    0.43
    ̈
    0.42
    ará
    0.42
    lombok
    0.42
    inz
    0.41
    Activations Density 0.000%

    No Known Activations