© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 129049
    Prev
    Next
    INDEX
    Explanations

    delineate, delineation, delineated

    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
    ↵↵
    -2.94
    {
    -2.48
    شير
    -2.09
    
    -2.02
     сказали
    -1.97
     hodiny
    -1.88
     }?>
    -1.88
    }
    -1.86
     Therefore
    -1.83
    .
    -1.82
    POSITIVE LOGITS
    䊐
    2.30
    谖
    2.28
    
    2.09
     TMPro
    2.06
     of
    2.00
     campeón
    1.99
     verschill
    1.98
    苼
    1.98
    ),”
    1.97
     totalmente
    1.94
    Activations Density 0.004%

    No Known Activations