© 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. 54103
    Prev
    Next
    INDEX
    Explanations

    tractor propeller

    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
    aporation
    -0.72
     paintball
    -0.70
     Friedman
    -0.69
     Shotgun
    -0.69
     milk
    -0.69
    Pipeline
    -0.68
     purses
    -0.67
     iCloud
    -0.66
     Affection
    -0.66
    iyi
    -0.66
    POSITIVE LOGITS
     propeller
    2.38
     prop
    2.34
     Prop
    2.03
    prop
    2.02
     props
    1.98
    Prop
    1.88
     blades
    1.88
    props
    1.76
     blade
    1.59
    Props
    1.53
    Activations Density 0.022%

    No Known Activations