© 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. 64903
    Prev
    Next
    INDEX
    Explanations

    Japanese capability or possibility

    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
     gouverneur
    -0.91
    ärt
    -0.89
    deutscher
    -0.88
     tef
    -0.86
    zat
    -0.84
    数组
    -0.82
     vitamina
    -0.81
    HttpSession
    -0.81
    taya
    -0.81
    Perl
    -0.81
    POSITIVE LOGITS
     people
    1.11
     times
    1.10
     daardoor
    0.97
     Then
    0.96
     or
    0.94
    ことを
    0.93
     if
    0.93
     then
    0.91
     wydaje
    0.91
    場合
    0.88
    Activations Density 0.001%

    No Known Activations