© 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. 10-GEMMASCOPE-RES-131K
    7. 12012
    Prev
    Next
    INDEX
    Explanations

    Bangladesh and associated institutions

    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
    嚶
    -2.39
    瑒
    -2.13
    統領
    -2.06
    睒
    -2.06
    を終
    -2.02
    錸
    -1.97
    TintMode
    -1.89
     bekämp
    -1.87
    嚒
    -1.83
     überprü
    -1.82
    POSITIVE LOGITS
    (
    2.06
    \"
    1.98
    =
    1.97
     of
    1.95
    ]
    1.88
     \"
    1.87
     Dieser
    1.84
    ↵
    1.81
    “
    1.79
     в
    1.74
    Activations Density 0.004%

    No Known Activations