© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 13008
    Prev
    Next
    INDEX
    Explanations

    css padding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
     градусов
    1.00
    sehen
    0.95
    更容易
    0.92
     mingle
    0.87
    偷偷
    0.87
     MyRegisterClass
    0.85
    ���
    0.85
     grey
    0.83
    印度
    0.83
     openai
    0.83
    POSITIVE LOGITS
    bottom
    0.92
    ра
    0.91
     sider
    0.88
    $=\
    0.84
    -
    0.83
    S
    0.82
     atrás
    0.81
    abha
    0.81
    й
    0.80
    Supplemental
    0.79
    Activations Density 0.008%

    No Known Activations