© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 30488
    Prev
    Next
    INDEX
    Explanations

    references to figures or tables

    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
     Table
    -1.19
    Table
    -1.10
     table
    -0.95
     tables
    -0.90
     TABLE
    -0.88
    table
    -0.87
    (",");
    -0.82
    TABLE
    -0.81
    テーブル
    -0.77
    orgon
    -0.75
    POSITIVE LOGITS
     EoL
    0.92
    闺
    0.92
     cesse
    0.86
    اقة
    0.84
    []){
    0.83
    ৎ
    0.83
    quema
    0.82
    険
    0.81
     作り方
    0.79
    らせる
    0.79
    Activations Density 0.008%

    No Known Activations