© 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. 11467
    Prev
    Next
    INDEX
    Explanations

    result of causality

    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
    </h1>
    -2.05
     *
    -1.94
    出了一
    -1.87
    <h3>
    -1.84
     antes
    -1.66
     ۷
    -1.66
     name
    -1.61
    所有人都
    -1.61
    一定的
    -1.59
     to
    -1.58
    POSITIVE LOGITS
    </em>
    2.09
    ㍉
    1.71
     結果
    1.69
     verhind
    1.68
     különböző
    1.65
     olika
    1.63
     berichten
    1.63
     bewegen
    1.61
     konfig
    1.60
     edelstahl
    1.57
    Activations Density 0.054%

    No Known Activations