© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 45640
    Prev
    Next
    INDEX
    Explanations

    baking cookies

    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
    financ
    0.49
    狯
    0.48
    FormParams
    0.47
     купи
    0.47
     द्विवेदी
    0.47
    住所
    0.47
     جوړونکو
    0.46
    いる
    0.46
    чего
    0.46
     lieux
    0.46
    POSITIVE LOGITS
     )
    0.46
        
    0.42
                             
    0.42
    .
    0.42
     warts
    0.41
     electrons
    0.40
                            
    0.39
     sewing
    0.39
     nails
    0.39
           
    0.39
    Activations Density 0.002%

    No Known Activations