© 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. 82344
    Prev
    Next
    INDEX
    Explanations

    code 128

    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
     tiegħ
    -0.83
    اعم
    -0.77
    alted
    -0.74
    unier
    -0.74
     सत्या
    -0.73
     consuma
    -0.72
    While
    -0.71
    ærk
    -0.71
    സ്
    -0.69
    What
    -0.69
    POSITIVE LOGITS
     était
    0.86
    finder
    0.85
    Mek
    0.82
     finder
    0.82
     struktur
    0.80
     Mek
    0.80
    Qe
    0.80
     версии
    0.79
     Reed
    0.77
     jupe
    0.77
    Activations Density 0.003%

    No Known Activations