© 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. 68192
    Prev
    Next
    INDEX
    Explanations

    raising awareness

    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
    ).
    -1.61
     the
    -1.59
     kämp
    -1.57
    $.
    -1.48
     wenigen
    -1.47
     spielte
    -1.46
    x
    -1.46
     intend
    -1.46
    начально
    -1.45
     are
    -1.45
    POSITIVE LOGITS
     イラストレーション
    1.86
     Ottobre
    1.85
    𖥦
    1.84
    龗
    1.83
    鏵
    1.81
    蘼
    1.80
    勠
    1.77
     onor
    1.77
     argento
    1.75
     
    1.74
    Activations Density 0.015%

    No Known Activations