© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1134
    Prev
    Next
    INDEX
    Explanations

    polite requests for information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
     })();
    1.88
    Macros
    1.72
     sendMessage
    1.71
    PropertyChanged
    1.68
    })();
    1.62
    getCurrent
    1.61
    ្នែក
    1.61
     microseconds
    1.61
    ﻅ
    1.61
     restable
    1.60
    POSITIVE LOGITS
     DVD
    1.93
     Disk
    1.73
     Album
    1.69
    DVD
    1.69
     folder
    1.67
     Folder
    1.59
    碟
    1.59
     Albums
    1.57
     DVDs
    1.57
     album
    1.55
    Activations Density 1.588%

    No Known Activations