© 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. 34-GEMMASCOPE-RES-131K
    7. 31004
    Prev
    Next
    INDEX
    Explanations

    numbers and code contexts

    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
     Nine
    -0.89
    4
    -0.81
     fourth
    -0.80
     have
    -0.80
    Odkazy
    -0.77
               
    -0.77
    ⁹
    -0.77
    厄
    -0.76
     fifth
    -0.75
    Nine
    -0.75
    POSITIVE LOGITS
                    
    1.07
    مپ
    0.96
     trio
    0.93
     üç
    0.87
     three
    0.86
    3
    0.79
     ثلاث
    0.79
    THREE
    0.78
    ieste
    0.77
    สาม
    0.77
    Activations Density 0.015%

    No Known Activations