© 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. 108511
    Prev
    Next
    INDEX
    Explanations

    locations after commas

    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
     zowel
    -0.98
    っていた
    -0.98
     krótk
    -0.97
     /(\
    -0.92
     vorgestellt
    -0.92
    zval
    -0.90
     \&
    -0.90
    昔から
    -0.90
    Ừ
    -0.89
     楽天
    -0.88
    POSITIVE LOGITS
     which
    1.07
     verdo
    1.00
     norvég
    0.93
     штат
    0.92
     a
    0.90
    «,
    0.88
     semangat
    0.88
     where
    0.88
    uuu
    0.87
    把我
    0.86
    Activations Density 0.081%

    No Known Activations