Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7642
    Prev
    Next
    INDEX
    Explanations

    rocket plane, orbital rocket, flying cars

    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
     q
    -0.82
     outdoor
    -0.78
     canal
    -0.77
    在庫
    -0.76
     केंद्र
    -0.75
     envers
    -0.74
     bike
    -0.68
    rophes
    -0.68
    码
    -0.67
     indoors
    -0.66
    POSITIVE LOGITS
     част
    0.96
     passenger
    0.94
     tourist
    0.94
     Tourism
    0.91
    passenger
    0.91
    VSS
    0.90
     tourism
    0.90
     Konk
    0.88
     commercial
    0.88
     commerciale
    0.87
    Activations Density 0.007%

    No Known Activations