© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 74734
    Prev
    Next
    INDEX
    Explanations

    ReLU function explanation

    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
    Negative Logits
                
    0.66
    \
    0.66
    >
    0.59
                    
    0.58
         
    0.56
                        
    0.55
    )
    0.55
    _
    0.54
          
    0.54
    ]
    0.54
    POSITIVE LOGITS
     bathing
    0.44
    醎
    0.44
    గాలు
    0.44
    द्योग
    0.42
    BSData
    0.42
    يدة
    0.42
    ヴィ
    0.42
     películas
    0.42
    hygine
    0.42
    ពេ
    0.41
    Activations Density 0.001%

    No Known Activations