© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 228
    Prev
    Next
    INDEX
    Explanations

    AI model responses

    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
    佢
    2.27
     adjournment
    2.08
    hoea
    2.04
     instalment
    1.99
     (£
    1.97
    她在
    1.97
    囝
    1.94
    挈
    1.94
     instalments
    1.92
    ouncement
    1.87
    POSITIVE LOGITS
     obey
    2.17
    7
    2.15
     FEEL
    2.10
     feel
    2.01
     aspire
    2.01
     perceive
    2.00
     belong
    1.97
     объекты
    1.93
     combust
    1.93
     respir
    1.91
    Activations Density 0.638%

    No Known Activations