© 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. 107339
    Prev
    Next
    INDEX
    Explanations

    greater fruit and vegetable

    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
     sarees
    -1.05
     lobsters
    -1.05
     antlers
    -1.01
     camels
    -0.99
     mussels
    -0.98
     ewes
    -0.93
    ależy
    -0.93
     oamenii
    -0.92
    isins
    -0.91
     termites
    -0.91
    POSITIVE LOGITS
     lymphocyte
    0.95
     and
    0.95
     nanoparticle
    0.89
    首次
    0.88
     appliance
    0.88
     vegetable
    0.86
     robot
    0.85
     tablet
    0.85
     veggie
    0.83
     headphone
    0.82
    Activations Density 0.570%

    No Known Activations