© 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. 73679
    Prev
    Next
    INDEX
    Explanations

    fresh air

    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
     Antal
    -0.70
     richting
    -0.67
     Freizeit
    -0.67
    🔐
    -0.66
    FREQ
    -0.64
     gomez
    -0.64
    ]|
    -0.63
    fiore
    -0.63
     pilot
    -0.62
     Sediment
    -0.61
    POSITIVE LOGITS
     fresh
    2.75
     air
    2.33
    fresh
    1.98
    Fresh
    1.95
     Fresh
    1.87
     oxygen
    1.86
     breathe
    1.86
     frische
    1.79
     breathing
    1.70
     refreshing
    1.70
    Activations Density 0.025%

    No Known Activations