© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 123775
    Prev
    Next
    INDEX
    Explanations

    another new item

    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
     notare
    -1.68
    4
    -1.65
     watu
    -1.59
    
    -1.59
     familiare
    -1.55
     UNIVE
    -1.54
     militare
    -1.54
    ARCHITECT
    -1.53
     onor
    -1.52
    
    -1.51
    POSITIVE LOGITS
     a
    1.88
    Both
    1.88
    })),
    1.69
    _
    1.66
    </h1>
    1.66
     HasFactory
    1.63
    峯
    1.62
     }]
    1.59
    both
    1.57
     padx
    1.56
    Activations Density 0.015%

    No Known Activations