© 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. 116979
    Prev
    Next
    INDEX
    Explanations

    garage

    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
    屣
    -1.16
    捽
    -1.09
    盍
    -1.04
    瞜
    -1.02
     verantwort
    -1.02
     penna
    -1.02
    覿
    -1.02
     vane
    -1.01
    луйста
    -1.00
    攆
    -0.99
    POSITIVE LOGITS
     Garage
    1.38
     garage
    1.30
    Garage
    1.21
     sale
    1.19
    mahal
    1.09
     Experiments
    1.08
     Ż
    1.05
     garages
    1.05
     conversions
    1.05
     door
    1.03
    Activations Density 0.005%

    No Known Activations