© 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. 108878
    Prev
    Next
    INDEX
    Explanations

    pairing devices or interactions

    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
    涧
    -0.82
    ieteur
    -0.81
     filtros
    -0.81
     transplants
    -0.78
    REVIEWS
    -0.77
     angepasst
    -0.77
     gesamte
    -0.77
    Lotto
    -0.77
    rania
    -0.76
    嗬
    -0.76
    POSITIVE LOGITS
     pairing
    2.69
    Pairing
    2.19
     Pairing
    2.11
    pairing
    2.06
     paired
    2.02
     pairings
    1.92
     pair
    1.70
    ペア
    1.59
     Pair
    1.55
    paired
    1.54
    Activations Density 0.032%

    No Known Activations