© 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. 84912
    Prev
    Next
    INDEX
    Explanations

    Ars Technica

    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
     -
    -0.93
    事了
    -0.90
     ==
    -0.79
    แห่ง
    -0.79
     –
    -0.78
     -}
    -0.77
     --
    -0.76
     ===
    -0.74
    閔
    -0.73
    closedir
    -0.72
    POSITIVE LOGITS
    —”
    1.06
    —"
    0.95
    習
    0.94
    —“
    0.90
    —
    0.85
    kowski
    0.82
    自行
    0.81
    덟
    0.80
     yep
    0.78
    झ
    0.77
    Activations Density 0.224%

    No Known Activations