© 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. 28815
    Prev
    Next
    INDEX
    Explanations

    business documents and records

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

    medical imaging, CLI, connection

    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
    á
    0.52
    é
    0.50
    怵
    0.49
    ışt
    0.47
    getChildren
    0.47
     解説
    0.45
    แห่ง
    0.45
     النصوص
    0.45
    ズム
    0.44
    eleaf
    0.44
    POSITIVE LOGITS
     outboard
    0.41
     stockpile
    0.41
     goof
    0.41
    ភ្ជាប់
    0.40
     floors
    0.40
     startup
    0.39
    퀄
    0.39
     floor
    0.39
     stash
    0.39
     ferry
    0.39
    Activations Density 0.011%

    No Known Activations