© 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. 7718
    Prev
    Next
    INDEX
    Explanations

    introducing reasons or explanations

    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
     они
    -1.90
    😲
    -1.81
    ⁍
    -1.80
    
    -1.80
    嗐
    -1.79
    🥵
    -1.78
     建筑
    -1.75
     醬
    -1.74
    XDD
    -1.73
     ग्राह
    -1.72
    POSITIVE LOGITS
     \
    2.48
     ponieważ
    2.41
    ‘
    2.19
    '
    2.19
    4
    2.02
    5
    1.98
    er
    1.97
    犼
    1.96
    6
    1.91
     którzy
    1.90
    Activations Density 0.003%

    No Known Activations