© 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. 6937
    Prev
    Next
    INDEX
    Explanations

    collateral and security, or secured by

    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
     APPROPRI
    -0.83
     congé
    -0.82
    Rental
    -0.82
     fieltro
    -0.80
    Външни
    -0.79
    parseColor
    -0.79
     Niles
    -0.78
    itoneum
    -0.78
     verhind
    -0.78
     éti
    -0.77
    POSITIVE LOGITS
     collateral
    4.16
     Collateral
    2.91
    Collateral
    2.91
    coll
    2.39
     coll
    1.94
     security
    1.89
     COLL
    1.67
    COLL
    1.57
     pledged
    1.53
     securing
    1.43
    Activations Density 0.029%

    No Known Activations