© 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. 72939
    Prev
    Next
    INDEX
    Explanations

    Ireland and Northern Ireland

    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
    '
    -2.20
    9
    -1.95
    ......
    -1.86
    7
    -1.84
    1
    -1.81
    デレ
    -1.80
     These
    -1.80
    0
    -1.77
    ..."
    -1.75
    仳
    -1.75
    POSITIVE LOGITS
    Ivoire
    2.17
    eronau
    2.06
    蔟
    2.02
    ),
    1.98
    medriver
    1.93
    而又
    1.91
    ی
    1.87
    ㌘
    1.85
    abortion
    1.84
    xdc
    1.82
    Activations Density 0.003%

    No Known Activations