© 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. 48513
    Prev
    Next
    INDEX
    Explanations

    facilitate communication and information access

    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
     TikTok
    -0.98
     Webseite
    -0.91
    alad
    -0.89
    centration
    -0.88
    Билгалдахарш
    -0.88
     Weibo
    -0.88
    seigneur
    -0.87
    mamm
    -0.86
    clientHeight
    -0.84
     subsequ
    -0.83
    POSITIVE LOGITS
     communication
    1.97
     communicate
    1.94
     information
    1.70
     connect
    1.67
     communicating
    1.61
    connect
    1.43
     communications
    1.40
    Communication
    1.38
    communication
    1.36
     conect
    1.33
    Activations Density 0.088%

    No Known Activations