© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86100
    Prev
    Next
    INDEX
    Explanations

    up to this point

    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>
    -1.87
    )
    -1.82
    </i>
    -1.80
    »),
    -1.80
    }
    -1.69
    </th>
    -1.68
    {
    -1.63
    OT
    -1.59
            
    -1.58
    AL
    -1.58
    POSITIVE LOGITS
    コロナ禍
    1.70
     suicidio
    1.66
    
    1.55
    '
    1.53
     aborto
    1.49
    服务的
    1.49
     Kräfte
    1.41
    ↑↑↑
    1.41
     capitalismo
    1.40
     București
    1.39
    Activations Density 0.008%

    No Known Activations