© 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. 10-GEMMASCOPE-RES-131K
    7. 85704
    Prev
    Next
    INDEX
    Explanations

    Spring Beans Configuration

    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_10/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
     tremendous
    -1.79
     amazing
    -1.75
    噲
    -1.74
     terrific
    -1.73
     behave
    -1.70
    中に
    -1.69
    仿佛
    -1.66
    品的
    -1.65
    parentId
    -1.62
    了的
    -1.60
    POSITIVE LOGITS
    ↵↵
    2.22
    }$
    1.77
    ção
    1.73
     him
    1.69
    々が
    1.67
    VIATIONS
    1.66
    tazione
    1.59
    ścić
    1.59
    这不
    1.55
    掟
    1.55
    Activations Density 0.002%

    No Known Activations