© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6951
    Prev
    Next
    INDEX
    Explanations

    AI descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    似乎
    0.46
    淉
    0.40
    imental
    0.40
     গল
    0.39
     LinearLayout
    0.39
    显示的
    0.39
    琏
    0.38
    bandSize
    0.38
     Logical
    0.38
    䀼
    0.37
    POSITIVE LOGITS
     celebrities
    0.52
     IMAX
    0.50
     uso
    0.48
     cidad
    0.48
    namento
    0.48
     journée
    0.48
     ടി
    0.47
     imprescind
    0.47
     deceiving
    0.47
     considéré
    0.46
    Activations Density 0.001%

    No Known Activations