© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77606
    Prev
    Next
    INDEX
    Explanations

    GitLab and geographic locations

    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
    ッサージ
    -0.78
    猖
    -0.71
    봇
    -0.70
     差
    -0.69
     JFK
    -0.69
     dificultad
    -0.69
    柝
    -0.69
    тивной
    -0.67
    érant
    -0.66
    〖
    -0.66
    POSITIVE LOGITS
    gitlab
    1.00
     Git
    0.87
    گي
    0.84
    Git
    0.82
     Shreveport
    0.82
     Bayou
    0.81
    Runners
    0.78
     handbook
    0.77
     Runners
    0.77
    runners
    0.75
    Activations Density 0.038%

    No Known Activations