© 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. 32231
    Prev
    Next
    INDEX
    Explanations

    culvert and drainage

    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
     ವಿ
    -0.89
    luss
    -0.78
    ēl
    -0.77
     Kiy
    -0.77
    stadium
    -0.75
    ļas
    -0.73
    鐨
    -0.73
    setSubject
    -0.72
    folios
    -0.71
    Bou
    -0.70
    POSITIVE LOGITS
     culvert
    2.56
     cul
    2.42
     Cul
    1.88
    Cul
    1.84
    cul
    1.78
     CUL
    1.40
    CUL
    1.27
     Culver
    1.20
     куль
    1.14
     pipes
    1.08
    Activations Density 0.019%

    No Known Activations