© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 92749
    Prev
    Next
    INDEX
    Explanations

    promote products and services

    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
    şağı
    -1.00
    stimulated
    -0.93
    把它
    -0.88
     kterou
    -0.86
    breviations
    -0.84
     którą
    -0.84
     большая
    -0.83
     เพื่อ
    -0.79
    からです
    -0.77
    ⅔
    -0.76
    POSITIVE LOGITS
     wares
    1.72
     products
    1.71
     virtues
    1.58
     services
    1.37
     auprès
    1.31
     capabilities
    1.30
     brand
    1.23
     awareness
    1.23
     advantages
    1.18
    products
    1.14
    Activations Density 0.049%

    No Known Activations