© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 64487
    Prev
    Next
    INDEX
    Explanations

    cons and disadvantages

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ){
    
    -1.20
    />
    
    -1.19
    };
    
    -1.13
     and
    -1.13
    }}
    
    -1.10
     requirement
    -1.09
     bereits
    -1.09
    }();
    -1.08
    ],
    
    -1.07
     され
    -1.06
    POSITIVE LOGITS
     of
    2.36
     each
    1.09
     墙
    1.07
     about
    1.02
     çi
    1.01
    こい
    1.00
     sauvages
    0.98
    pros
    0.98
     weder
    0.97
     vandens
    0.96
    Activations Density 0.013%

    No Known Activations