© 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. 62897
    Prev
    Next
    INDEX
    Explanations

    social activist and community engagement

    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
     udang
    -0.99
    dafx
    -0.95
     kolam
    -0.91
    gupta
    -0.87
     kompetisi
    -0.86
    lamda
    -0.86
     gatto
    -0.85
    getShared
    -0.84
    álja
    -0.84
     Приступљено
    -0.83
    POSITIVE LOGITS
     spread
    1.13
     spreading
    1.05
     donations
    1.05
     rural
    1.02
     society
    1.00
     Spreading
    0.96
     Aufklärung
    0.94
     sensi
    0.94
     village
    0.93
     campaign
    0.92
    Activations Density 0.030%

    No Known Activations