© 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. 37849
    Prev
    Next
    INDEX
    Explanations

    Arthur followed by surname

    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
    mnar
    -0.87
     considera
    -0.87
    ベット
    -0.86
    adora
    -0.85
     творчества
    -0.84
     気
    -0.84
    Lähde
    -0.82
    📛
    -0.82
    ígenes
    -0.82
     voto
    -0.82
    POSITIVE LOGITS
    但是
    0.92
    如果
    0.79
    げん
    0.77
     Arthur
    0.77
     estrenar
    0.75
    fR
    0.75
     Erlebn
    0.74
     Effective
    0.71
     destacó
    0.69
    0.69
    Activations Density 0.022%
    No Known Activations