© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 32388
    Prev
    Next
    INDEX
    Explanations

    introduces specific details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ‘’
    -1.02
     The
    -1.02
     vermutlich
    -0.94
     ''
    -0.93
     {\
    -0.92
     "
    -0.91
     You
    -0.91
    !!"
    -0.90
    ご了承ください
    -0.90
    Приятного
    -0.88
    POSITIVE LOGITS
    ................
    2.58
                               
    1.85
                           
    1.84
                       
    1.79
                            
    1.78
    ........
    1.74
    ...............
    1.73
                        
    1.72
    ..............
    1.71
    ............
    1.70
    Activations Density 0.047%

    No Known Activations