© 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. 76134
    Prev
    Next
    INDEX
    Explanations

    software license documentation

    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
    eman
    -0.87
    aughan
    -0.84
     Emer
    -0.84
    ITÉ
    -0.81
    JO
    -0.78
    ];
    -0.77
     ayudará
    -0.77
    ]$,
    -0.77
    ()];
    -0.76
    EMAN
    -0.76
    POSITIVE LOGITS
    ائه
    0.83
    тение
    0.80
     столо
    0.79
    힣
    0.77
    eze
    0.74
    Huy
    0.74
     siena
    0.70
    čené
    0.69
    感的
    0.69
     świata
    0.69
    Activations Density 0.002%

    No Known Activations