© 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. 48054
    Prev
    Next
    INDEX
    Explanations

    back

    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
    superior
    -0.86
    arlı
    -0.82
     aspects
    -0.80
    Crunch
    -0.80
     REGARD
    -0.79
     superior
    -0.78
    scrap
    -0.74
     REQUIRE
    -0.74
     greater
    -0.74
    Chips
    -0.73
    POSITIVE LOGITS
    hedra
    0.99
    ReadLine
    0.81
    炙
    0.81
    else
    0.81
    。。
    0.81
    、、
    0.80
    ValueError
    0.77
    month
    0.74
    道的
    0.74
     windshield
    0.74
    Activations Density 0.020%

    No Known Activations