© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8002
    Prev
    Next
    INDEX
    Explanations

    holding, held, and holds

    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
    )
    -2.50
    s
    -2.17
     affect
    -2.13
     ใหญ่
    -2.11
     插画
    -2.06
    薅
    -2.02
     Traditionally
    -2.00
    bilisi
    -2.00
    kadang
    -1.98
     Article
    -1.96
    POSITIVE LOGITS
    )
    2.83
    ”;
    2.56
    ”)
    2.56
    }]
    2.44
    ”,
    2.41
    ”，
    2.34
    ();
    2.31
    ）
    2.25
    ")
    2.20
    ”:
    2.17
    Activations Density 0.002%

    No Known Activations