© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6502
    Prev
    Next
    INDEX
    Explanations

    encouraged or build pipeline

    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_24_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
     वर्षीय
    0.82
    тых
    0.79
     Psychiatry
    0.75
    摹
    0.73
     اﻻ
    0.72
     слы
    0.71
     देहरादून
    0.71
     αποτέ
    0.71
     психи
    0.70
     ARCH
    0.69
    POSITIVE LOGITS
    esor
    0.95
    {
    0.81
     mantenere
    0.81
    >
    0.81
     branchNode
    0.80
    zor
    0.80
     afer
    0.79
    nam
    0.78
    assurer
    0.78
    /
    0.76
    Activations Density 0.002%

    No Known Activations