© 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. 70122
    Prev
    Next
    INDEX
    Explanations

    code tags and markup

    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
    <strong>
    -0.96
    atung
    -0.85
    CrossOrigin
    -0.82
    τέλε
    -0.79
    ורות
    -0.77
    <tfoot>
    -0.75
    lts
    -0.73
    ?\\
    -0.73
     zawiera
    -0.73
     Woche
    -0.73
    POSITIVE LOGITS
    </b>
    3.34
    </i>
    2.11
    </strong>
    2.05
    </u>
    1.66
    </em>
    1.50
    </code>
    1.23
    </h4>
    1.14
    </sup>
    1.09
    </h2>
    1.02
    </h5>
    0.95
    Activations Density 0.012%

    No Known Activations