© 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. 10-GEMMASCOPE-RES-131K
    7. 104137
    Prev
    Next
    INDEX
    Explanations

    memory and solid

    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
     ―
    -2.11
     consiguió
    -2.03
    ).
    -2.02
    ]
    -1.98
     juſ
    -1.98
     thee
    -1.94
     ‘‘
    -1.93
     ehemalige
    -1.92
     niyang
    -1.91
    縯
    -1.90
    POSITIVE LOGITS
     contemporáneo
    2.05
    </h3>
    1.98
    If
    1.91
     literario
    1.89
    This
    1.88
     でも
    1.81
    鹩
    1.80
    熥
    1.78
    ぁ
    1.77
    駱
    1.77
    Activations Density 0.115%

    No Known Activations