© 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. 55849
    Prev
    Next
    INDEX
    Explanations

    encourages, uplifts, and blesses

    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
    visibility
    -0.97
     nø
    -0.91
     revenge
    -0.90
    mici
    -0.89
    fonds
    -0.85
    嬉
    -0.84
    ZIONE
    -0.84
     CONTROL
    -0.83
     idiomas
    -0.83
    couts
    -0.81
    POSITIVE LOGITS
     uplifting
    1.57
     uplift
    1.54
     edific
    1.34
     nourishment
    1.32
     bless
    1.29
     strengthening
    1.24
     nourish
    1.23
     blessing
    1.22
     strengthen
    1.22
     nour
    1.19
    Activations Density 0.020%

    No Known Activations