© 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. 21223
    Prev
    Next
    INDEX
    Explanations

    code definitions and array manipulation

    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
     It
    -2.00
     to
    -1.96
    <
    -1.83
    In
    -1.78
        
    -1.75
     and
    -1.67
    ia
    -1.61
              
    -1.60
           
    -1.60
          
    -1.59
    POSITIVE LOGITS
     of
    3.31
     vokal
    1.93
     zestawie
    1.93
     our
    1.92
    檍
    1.80
     your
    1.73
    甞
    1.70
    demás
    1.70
     horarios
    1.70
    靫
    1.69
    Activations Density 0.002%

    No Known Activations