© 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. 5154
    Prev
    Next
    INDEX
    Explanations

    detects or triggers

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

    conditional server events

    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
    你們
    0.47
    漫畫
    0.42
    學校
    0.42
    薩
    0.41
    偉
    0.40
    त्त
    0.40
     वस्त्र
    0.40
    文學
    0.40
    學院
    0.39
    廡
    0.39
    POSITIVE LOGITS
     detected
    0.70
     HTTP
    0.59
     detects
    0.58
     triggered
    0.57
     Detected
    0.55
     timestamp
    0.55
    触发
    0.54
     trigger
    0.54
     détecter
    0.53
     triggering
    0.52
    Activations Density 0.426%

    No Known Activations