© 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. 59039
    Prev
    Next
    INDEX
    Explanations

    html/xml tags

    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
     earliest
    -1.91
    </h3>
    -1.85
     созда
    -1.58
     eases
    -1.56
    <td>
    -1.52
    氳
    -1.52
     conhe
    -1.52
    </strong>
    -1.51
     ability
    -1.51
    鈊
    -1.48
    POSITIVE LOGITS
    
    2.02
    imanapun
    1.80
    erweise
    1.76
    )»
    1.63
    鼉
    1.63
     Tenggara
    1.62
    😓
    1.61
    )++;
    1.59
    !«
    1.59
     cristianos
    1.59
    Activations Density 0.007%

    No Known Activations