© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 124650
    Prev
    Next
    INDEX
    Explanations

    being engaged in or dealing with

    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
    </b>
    -1.91
    伋
    -1.84
    '
    -1.74
    </td>
    -1.73
     mergul
    -1.71
    </i>
    -1.69
    璈
    -1.67
    </h1>
    -1.67
     testemun
    -1.65
    </h5>
    -1.62
    POSITIVE LOGITS
    </strong>
    2.05
     When
    1.70
    </em>
    1.64
     For
    1.63
    acji
    1.59
     Although
    1.57
     However
    1.52
    水瓶
    1.50
    reuung
    1.48
    Теперь
    1.45
    Activations Density 0.009%

    No Known Activations