© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 80934
    Prev
    Next
    INDEX
    Explanations

    locations near or outside

    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
    فهوم
    -0.96
     and
    -0.86
    仇
    -0.82
     parmi
    -0.82
     lorsqu
    -0.80
    ͜
    -0.77
    底下
    -0.73
    sedown
    -0.71
     berechtigt
    -0.71
     siitä
    -0.70
    POSITIVE LOGITS
     near
    4.78
     outside
    3.66
    near
    3.56
     près
    2.94
     Near
    2.86
    Near
    2.83
    outside
    2.64
    Outside
    2.45
     in
    2.38
     NEAR
    2.31
    Activations Density 0.223%

    No Known Activations