© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91956
    Prev
    Next
    INDEX
    Explanations

    combining lists and data structures

    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_34/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
    鵜
    -0.82
    Each
    -0.81
     rừng
    -0.80
    ранда
    -0.75
     heated
    -0.75
     organizado
    -0.74
    guarda
    -0.73
    activo
    -0.72
    開き
    -0.71
     convertirse
    -0.71
    POSITIVE LOGITS
    concat
    2.17
     union
    1.95
     concat
    1.83
     combined
    1.80
    union
    1.77
    Concat
    1.77
     append
    1.76
     combine
    1.74
    append
    1.67
    concatenate
    1.63
    Activations Density 0.022%

    No Known Activations