© 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. 21640
    Prev
    Next
    INDEX
    Explanations

    writing to

    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
        
    -2.14
    "
    -2.09
    '
    -1.77
     manchen
    -1.70
     "
    -1.65
    </h2>
    -1.65
    </em>
    -1.64
    後
    -1.61
     make
    -1.59
     geringer
    -1.57
    POSITIVE LOGITS
    
    2.05
     eſſ
    2.05
    鶿
    1.98
    啻
    1.86
     controladores
    1.84
    嘏
    1.80
    ٙ
    1.78
    渼
    1.74
     ajedrez
    1.73
     öğretmen
    1.70
    Activations Density 0.012%

    No Known Activations