© 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. 99145
    Prev
    Next
    INDEX
    Explanations

    purchasing and replacing

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

    counting, measurement, replacement

    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
     vulnerabilities
    0.46
     screenshots
    0.46
    autres
    0.45
     vulnerability
    0.44
     ಅಪಾಯ
    0.44
    ˗
    0.43
    脆弱
    0.43
     controllability
    0.43
     ก่อน
    0.42
     ಸಮಸ್ಯೆ
    0.42
    POSITIVE LOGITS
    কিন
    0.55
     една
    0.52
    Expensive
    0.52
    买
    0.51
    лле
    0.50
    购买
    0.50
    кви
    0.50
    购置
    0.49
     reempl
    0.49
     sostitu
    0.49
    Activations Density 0.003%

    No Known Activations