© 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. 44789
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names

    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
    逦
    -3.33
     When
    -3.25
     During
    -3.16
     While
    -2.98
     Shortly
    -2.89
     Despite
    -2.78
     Throughout
    -2.78
     Regardless
    -2.72
     Those
    -2.72
     With
    -2.72
    POSITIVE LOGITS
    氿
    3.13
    ༀ
    3.00
     FIVE
    2.97
    寕
    2.81
    ⸫
    2.77
     THREE
    2.69
    добно
    2.64
    锖
    2.64
    憷
    2.63
    ⏑
    2.63
    Activations Density 0.075%

    No Known Activations