© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22019
    Prev
    Next
    INDEX
    Explanations

    late 1980s or 1990s

    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
    </td>
    -2.36
    </i>
    -1.87
    籥
    -1.82
    </b>
    -1.78
    medriver
    -1.70
    汩
    -1.56
    </h5>
    -1.52
                          
    -1.51
     rique
    -1.48
    </caption>
    -1.42
    POSITIVE LOGITS
     unsurpassed
    1.67
     Kampagne
    1.60
    жество
    1.53
    8
    1.52
     его
    1.51
    7
    1.45
    増えて
    1.45
    6
    1.44
    9
    1.38
     traditionellen
    1.38
    Activations Density 0.032%

    No Known Activations