© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 9052
    Prev
    Next
    INDEX
    Explanations

    GPU, VRAM, GB

    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
     финансо
    1.00
    <unused2164>
    0.94
     वित्तीय
    0.91
    adeso
    0.91
     dehuman
    0.91
     콘텐츠
    0.89
    цької
    0.88
     आर्थिक
    0.87
     фармацев
    0.87
     социально
    0.86
    POSITIVE LOGITS
     M
    0.98
     V
    0.98
     max
    0.98
     X
    0.98
     H
    0.96
     Max
    0.96
     L
    0.95
     with
    0.94
     ported
    0.93
     G
    0.93
    Activations Density 0.402%

    No Known Activations