© 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-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 12704
    Prev
    Next
    INDEX
    Explanations

    finance and funding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ्स
    1.89
    ا
    1.58
    ן
    1.50
     चूंकि
    1.48
    ul
    1.41
    ে
    1.41
    ătoare
    1.39
    ઓ
    1.39
    IAN
    1.38
    ו
    1.37
    POSITIVE LOGITS
    ৪
    2.06
     untouched
    1.93
     bourbon
    1.87
     thunderstorms
    1.87
     backtracking
    1.87
     πάντα
    1.86
     ibuprofen
    1.84
     encir
    1.82
     autopilot
    1.79
     jeopard
    1.76
    Activations Density 0.045%

    No Known Activations