© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 130204
    Prev
    Next
    INDEX
    Explanations

    wedding and ceremony roles

    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
    ”？
    -2.06
    codable
    -1.69
     ANOTHER
    -1.66
     manchmal
    -1.62
     informieren
    -1.52
     NOTHING
    -1.52
    ៚
    -1.52
     После
    -1.52
    uitton
    -1.49
    </h4>
    -1.48
    POSITIVE LOGITS
    </i>
    2.23
    Ꮸ
    1.72
    "));
    1.61
    </sub>
    1.55
    </h3>
    1.45
    Ᏸ
    1.41
    ݯ
    1.41
     vesel
    1.38
    efore
    1.31
    Inicial
    1.30
    Activations Density 0.004%

    No Known Activations