© 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. 108459
    Prev
    Next
    INDEX
    Explanations

    titles and media works

    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
    剧照
    -0.98
    剧本
    -0.90
    haul
    -0.81
    ȯ
    -0.76
    throated
    -0.75
    irled
    -0.75
    liśmy
    -0.75
     poem
    -0.74
     Cedex
    -0.74
     undang
    -0.73
    POSITIVE LOGITS
     invested
    0.94
     investors
    0.93
    尺
    0.89
    《
    0.89
    投資
    0.86
     movie
    0.83
     adapted
    0.83
    投资
    0.81
    rachtet
    0.81
     works
    0.79
    Activations Density 0.010%

    No Known Activations