© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2151
    Prev
    Next
    INDEX
    Explanations

    Saturday Night Live

    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
     avión
    -0.81
    ⇌
    -0.79
    駆
    -0.77
    znych
    -0.75
    この記事
    -0.73
     patrimonio
    -0.71
    ępnie
    -0.70
    obacz
    -0.70
    ーツ
    -0.69
    endcsname
    -0.68
    POSITIVE LOGITS
     SAT
    0.92
     Sat
    0.81
     пара
    0.80
    ემ
    0.79
    Caprio
    0.77
     Sati
    0.76
    ทุน
    0.75
     Nimbus
    0.74
     Erne
    0.73
    ډ
    0.73
    Activations Density 0.026%

    No Known Activations