© 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. 71862
    Prev
    Next
    INDEX
    Explanations

    event and delegate definitions

    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
    ’，
    -1.73
          
    -1.65
    erapeutics
    -1.62
        
    -1.61
    捽
    -1.60
    _
    -1.56
     productivo
    -1.55
    または
    -1.55
     каждом
    -1.48
     southeastern
    -1.47
    POSITIVE LOGITS
     például
    2.06
     őket
    2.03
     esimerkiksi
    1.79
     \%$
    1.78
    黑色的
    1.69
    mockMvc
    1.66
    .
    1.63
    ).
    1.56
    ción
    1.52
    ÍTULO
    1.51
    Activations Density 0.003%

    No Known Activations