© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 50258
    Prev
    Next
    INDEX
    Explanations

    collection/structure followed by close parenthesis

    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
     and
    -1.38
     />;
    -0.96
     even
    -0.96
    ;
    -0.95
    }$;
    -0.93
    ]];
    -0.92
    ];
    -0.91
     their
    -0.85
     aDecoder
    -0.84
     целом
    -0.83
    POSITIVE LOGITS
    )
    1.54
    ())
    1.33
    ){
    1.23
    "){
    1.15
    ){
    1.11
    )
    1.10
    `)
    1.10
    ")
    1.10
    :")
    1.09
     ){
    1.06
    Activations Density 0.008%

    No Known Activations