© 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. 108650
    Prev
    Next
    INDEX
    Explanations

    Far East

    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
    loč
    -0.86
    кономи
    -0.85
    フル
    -0.81
    🏂
    -0.80
     黄
    -0.80
    grö
    -0.79
    本科
    -0.79
     ktore
    -0.77
     punya
    -0.76
    ownie
    -0.76
    POSITIVE LOGITS
     Far
    0.94
    Far
    0.83
    far
    0.82
    ..
    0.79
     FAR
    0.77
     far
    0.75
    リンゴ
    0.74
     Soon
    0.71
     Fat
    0.70
     bessere
    0.70
    Activations Density 0.019%

    No Known Activations