© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 965
    Prev
    Next
    INDEX
    Explanations

    travel sales and taxes

    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
    atmosfera
    -0.89
    onStop
    -0.74
     Vaters
    -0.74
     одежду
    -0.73
     overnight
    -0.73
     Schal
    -0.73
     qualità
    -0.73
    ੧
    -0.72
    adne
    -0.71
    ኣ
    -0.71
    POSITIVE LOGITS
     TRAVEL
    0.96
     特典
    0.90
     travel
    0.89
    TRAVEL
    0.84
     fré
    0.82
     permett
    0.82
     prépar
    0.81
    Sales
    0.80
     SALES
    0.79
     complément
    0.79
    Activations Density 0.023%

    No Known Activations