© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2476
    Prev
    Next
    INDEX
    Explanations

    international languages and requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     (
    1.95
     v
    1.92
    V
    1.82
    v
    1.82
     V
    1.80
     P
    1.79
     one
    1.78
     One
    1.76
    P
    1.73
     Di
    1.70
    POSITIVE LOGITS
    rinsic
    2.13
     makeSound
    2.01
    هایت
    1.99
    个体
    1.87
     bodega
    1.85
     mascul
    1.75
     árabe
    1.71
     tokenId
    1.68
     ارد
    1.68
    ukun
    1.66
    Activations Density 0.042%

    No Known Activations