© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 3524
    Prev
    Next
    INDEX
    Explanations

    listing items and facts

    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
     body
    1.10
    ams
    1.08
    α
    1.03
     abstract
    1.01
    am
    0.97
    card
    0.97
    body
    0.96
    課
    0.96
     blood
    0.95
    тки
    0.94
    POSITIVE LOGITS
     Kiến
    1.48
     hoàn
    1.37
     อย่าง
    1.36
     Progn
    1.35
     situasi
    1.35
     Phần
    1.33
     Sử
    1.32
     mengatasi
    1.32
     alcançar
    1.31
     largement
    1.31
    Activations Density 0.049%

    No Known Activations