© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76886
    Prev
    Next
    INDEX
    Explanations

    road trips and roadhouses

    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
    ாம
    -0.91
    囪
    -0.90
    TagHelper
    -0.88
    ილ
    -0.88
     棒
    -0.87
          
    -0.87
                   
    -0.85
    দের
    -0.85
    dcmtk
    -0.84
     aDecoder
    -0.84
    POSITIVE LOGITS
    🛣
    1.22
     Agrega
    1.20
    road
    1.09
     leading
    1.03
    side
    1.02
    stead
    1.02
    kill
    0.99
     road
    0.98
    bed
    0.98
    blocks
    0.96
    Activations Density 0.022%

    No Known Activations