© 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-16K
    7. 8822
    Prev
    Next
    INDEX
    Explanations

    next week, hoping, located

    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_16k_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
    觎
    0.48
     cheeky
    0.47
     jokingly
    0.46
     bullshit
    0.46
    僭
    0.45
     sarcastic
    0.45
     misog
    0.45
     comedic
    0.44
     fucking
    0.44
     sämt
    0.43
    POSITIVE LOGITS
             
    0.45
         
    0.43
     during
    0.41
    from
    0.40
    IN
    0.40
    during
    0.40
                
    0.40
    ↵↵
    0.39
    electrical
    0.39
        
    0.39
    Activations Density 0.003%

    No Known Activations