© 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. 34632
    Prev
    Next
    INDEX
    Explanations

    material feeding hoppers

    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
     boiled
    -0.86
     coolant
    -0.84
    soaked
    -0.82
    Collateral
    -0.81
     refrigerant
    -0.80
     beber
    -0.79
    Pools
    -0.78
    ENCIL
    -0.77
    舒适
    -0.77
     water
    -0.77
    POSITIVE LOGITS
     hopper
    1.84
     chute
    1.20
     Hopper
    1.18
     feeder
    1.16
     bin
    1.16
     feed
    1.16
     feeders
    1.12
    сыпа
    1.10
     granular
    1.09
     silo
    1.08
    Activations Density 0.095%

    No Known Activations