© 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. 37892
    Prev
    Next
    INDEX
    Explanations

    Eagle Scout

    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
    witch
    -0.87
     Maki
    -0.84
    
    -0.80
    CRI
    -0.79
     Peres
    -0.77
    witches
    -0.75
    INPUTS
    -0.71
     תפ
    -0.70
     Heine
    -0.70
     modific
    -0.70
    POSITIVE LOGITS
     Eagle
    2.75
     scout
    2.36
     Boy
    2.27
    Eagle
    2.22
     Scout
    2.17
     scouts
    2.00
     Scouts
    1.98
     Troop
    1.97
     troop
    1.95
     Scouting
    1.93
    Activations Density 0.019%

    No Known Activations