© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 102410
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers followed by overall

    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
    readFileSync
    -0.73
    لاثة
    -0.72
    geon
    -0.72
    rophi
    -0.71
     Heilig
    -0.70
     dü
    -0.69
     gepf
    -0.67
    headed
    -0.67
    niejs
    -0.66
    ferd
    -0.66
    POSITIVE LOGITS
     overall
    3.38
     Overall
    2.84
    Overall
    2.81
    overall
    2.73
    OVERALL
    1.95
     overal
    1.87
    整体
    1.62
     overalls
    1.50
     Gesamt
    1.49
     keseluruhan
    1.46
    Activations Density 0.029%

    No Known Activations