© 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. 69887
    Prev
    Next
    INDEX
    Explanations

    automotive parts and features

    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
    块钱
    -0.83
    GYPT
    -0.81
    がある
    -0.78
     subido
    -0.76
     Wünsche
    -0.75
    ResponseModel
    -0.75
     μεγαλ
    -0.75
     ம
    -0.74
    ChildIndex
    -0.74
    🚅
    -0.73
    POSITIVE LOGITS
     trajets
    1.04
     Manganese
    0.94
     Package
    0.94
     beckon
    0.93
    ***********/
    0.92
     Pied
    0.90
     PACKAGE
    0.90
    amir
    0.90
     manganese
    0.89
     '+'
    0.88
    Activations Density 0.027%

    No Known Activations