© 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-3-12B
    5. 12-GEMMASCOPE-2-RES-16K
    7. 219
    Prev
    Next
    INDEX
    Explanations

    for purposes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_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
    د
    0.84
    Eds
    0.76
    ی
    0.76
    ه
    0.74
    داد
    0.72
    ে
    0.71
    ARG
    0.71
    HB
    0.69
    ない
    0.69
    রাই
    0.68
    POSITIVE LOGITS
     purposes
    0.87
    /***
    0.64
     betterment
    0.64
    io
    0.61
    ної
    0.61
     instance
    0.61
     awhile
    0.60
    or
    0.59
    hma
    0.59
     Purposes
    0.59
    Activations Density 0.937%

    No Known Activations