© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11653
    Prev
    Next
    INDEX
    Explanations

    argument . wine . the . ”. las

    np_acts-logits-general · gemini-2.5-flash-lite

    recursion depth

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    0.86
    if
    0.77
        
    0.70
    0.70
                
    0.68
            
    0.67
         
    0.67
     Data
    0.64
              
    0.63
    """
    0.63
    POSITIVE LOGITS
    OLYBDENUM
    0.72
     exud
    0.71
     tubercul
    0.70
     balsam
    0.68
     sillons
    0.68
     vasomotor
    0.68
     hepat
    0.67
     sarcom
    0.67
     ferrug
    0.66
     bicarbonate
    0.66
    Activations Density 0.003%

    No Known Activations