© 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-262K
    7. 36151
    Prev
    Next
    INDEX
    Explanations

    dy/dx

    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_262k_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
    
    0.97
     вторая
    0.91
     первая
    0.90
    োগ্র
    0.89
     הט
    0.89
    定位
    0.87
    ﻁ
    0.86
     افز
    0.86
     необходимости
    0.86
     биологи
    0.85
    POSITIVE LOGITS
    0.99
    0.89
    0.87
    d
    0.82
    0.80
    on
    0.78
                  
    0.78
     donne
    0.77
     on
    0.76
     from
    0.73
    Activations Density 0.001%

    No Known Activations