© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 43798
    Prev
    Next
    INDEX
    Explanations

    disproportionately affected

    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_10/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
    巔
    -2.25
     noteworthy
    -2.22
     tehd
    -2.16
     emblematic
    -2.16
     hallowed
    -2.14
    両方
    -2.14
    我还
    -2.03
    我好
    -2.02
     religiously
    -1.99
     individualized
    -1.98
    POSITIVE LOGITS
    ”;
    2.61
    ]));
    2.59
    </td>
    2.55
    ];
    
    2.55
    );
    
    2.53
                       
    2.47
    %).
    2.41
     (‘
    2.34
                                
    2.31
    纈
    2.31
    Activations Density 0.002%

    No Known Activations