© 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. 193364
    Prev
    Next
    INDEX
    Explanations

    stand out of / stick out from

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

    identifying PII/CII

    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
    婚礼
    0.57
    Halloween
    0.53
    一流
    0.50
    やお
    0.49
    sá
    0.49
    lemme
    0.49
    pro
    0.47
    ๔
    0.47
    parentId
    0.46
    Buildings
    0.45
    POSITIVE LOGITS
     easily
    0.52
     markets
    0.49
     '--
    0.48
    ळख
    0.48
     moieties
    0.47
     accounts
    0.46
     democracies
    0.46
     explorers
    0.45
     stabilizers
    0.45
     displays
    0.44
    Activations Density 0.000%

    No Known Activations