© 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. 14114
    Prev
    Next
    INDEX
    Explanations

    private events, individuals, and services

    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
    '
    -2.70
     I
    -2.09
    </strong>
    -2.06
    )
    -2.05
      
    -2.05
     are
    -2.02
     
    -1.98
    </h2>
    -1.97
            
    -1.96
                                   
    -1.96
    POSITIVE LOGITS
    Даже
    2.06
     maquillaje
    2.06
    鋮
    2.03
    Второй
    2.02
    瑧
    1.97
    喁
    1.94
    閬
    1.91
     間取り
    1.90
    Even
    1.90
    Despite
    1.88
    Activations Density 0.014%

    No Known Activations