© 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. 32287
    Prev
    Next
    INDEX
    Explanations

    analysis and analytical texts

    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
    每一个
    -0.86
    らが
    -0.85
    第一个
    -0.85
     brasil
    -0.76
     Theil
    -0.74
     ジュ
    -0.74
     ehrlich
    -0.74
    憺
    -0.73
    一口
    -0.71
     rask
    -0.70
    POSITIVE LOGITS
     naš
    0.81
    恤
    0.79
    Chim
    0.77
    chim
    0.74
    tue
    0.74
     stubble
    0.74
     sing
    0.72
    Stav
    0.72
     Chili
    0.72
     Vermögens
    0.72
    Activations Density 0.022%

    No Known Activations