© 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. 73683
    Prev
    Next
    INDEX
    Explanations

    receive promotional communications

    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
     перено
    -0.90
     الوزراء
    -0.80
     necesitaba
    -0.76
     abor
    -0.75
     необхід
    -0.75
     Schwert
    -0.73
     хороший
    -0.73
    btnBack
    -0.71
     methylene
    -0.71
     hôm
    -0.71
    POSITIVE LOGITS
     marketing
    2.38
    marketing
    1.97
    Marketing
    1.86
     communications
    1.68
     Marketing
    1.55
    communications
    1.54
     promotional
    1.53
     communication
    1.44
     MARKETING
    1.40
    Communications
    1.38
    Activations Density 0.039%

    No Known Activations