© 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. 1460
    Prev
    Next
    INDEX
    Explanations

    C union declarations

    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
    lectable
    -0.82
     its
    -0.80
    alet
    -0.80
     Zusammenarbeit
    -0.77
     Weiterbildung
    -0.74
    日で
    -0.72
    cps
    -0.71
     oraș
    -0.71
    gale
    -0.71
    bici
    -0.70
    POSITIVE LOGITS
     union
    2.61
    union
    2.45
     unions
    2.02
    Union
    1.91
     Union
    1.91
    UNION
    1.80
     UNION
    1.70
     Unions
    1.63
     Unión
    1.08
     unión
    1.05
    Activations Density 0.021%

    No Known Activations