© 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. 9592
    Prev
    Next
    INDEX
    Explanations

    checker dama

    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
    {
    -2.13
    </sup>
    -2.08
    </h4>
    -2.06
     após
    -1.78
    </h2>
    -1.78
    </td>
    -1.73
     stirs
    -1.73
    ჻
    -1.73
    鵜
    -1.70
    言った
    -1.70
    POSITIVE LOGITS
     itſelf
    1.86
     silueta
    1.77
     Bakter
    1.77
     Palembang
    1.73
     castel
    1.66
     "")
    1.64
     befolk
    1.64
     bestia
    1.63
     мои
    1.61
     "",
    1.59
    Activations Density 0.006%

    No Known Activations