© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59151
    Prev
    Next
    INDEX
    Explanations

    promote and enhance outcomes

    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
    時半
    -0.89
    Ĝ
    -0.88
     Portugu
    -0.84
    steak
    -0.84
    cress
    -0.81
     disminuir
    -0.81
    鱨
    -0.81
    。
    -0.81
    ụy
    -0.81
    ريك
    -0.80
    POSITIVE LOGITS
     promote
    3.88
     encourage
    3.55
     promoting
    3.45
     promotes
    3.28
     foster
    3.23
     encourages
    3.16
     Promote
    3.02
     encouraging
    2.98
    promote
    2.94
    Encourage
    2.94
    Activations Density 0.248%

    No Known Activations