© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13270
    Prev
    Next
    INDEX
    Explanations

    dialog boxes popups

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

    modal dialog popup

    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_16k_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
    蚀
    0.47
    เซ
    0.46
    掌控
    0.44
    ARRAY
    0.44
    鄢
    0.43
    レット
    0.43
    瓷
    0.42
    Լ
    0.42
    รม
    0.42
    浿
    0.42
    POSITIVE LOGITS
     modal
    1.17
     dialog
    1.05
     Modal
    1.02
     modals
    0.98
    modal
    0.96
    Modal
    0.95
     popup
    0.93
     dialogues
    0.93
     Dialog
    0.91
    Dialog
    0.87
    Activations Density 0.113%

    No Known Activations