© 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-65K
    7. 6978
    Prev
    Next
    INDEX
    Explanations

    link to doi

    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_65k_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
     جہاں
    0.85
    资源
    0.84
    ፦
    0.80
     طریق
    0.78
    łada
    0.78
     quản
    0.77
     মানে
    0.76
     ресурсы
    0.75
     gdzie
    0.75
    然後
    0.74
    POSITIVE LOGITS
     too
    0.81
    too
    0.76
     accordingly
    0.75
     anew
    0.72
     Too
    0.70
     п
    0.62
    ೆಗೆ
    0.60
     leite
    0.59
     слишком
    0.58
     TOO
    0.57
    Activations Density 0.000%

    No Known Activations