© 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. 6993
    Prev
    Next
    INDEX
    Explanations

    years and numbers

    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
    wiście
    -0.94
     မ
    -0.89
     otro
    -0.84
    窍
    -0.84
     Isol
    -0.83
     Apoptosis
    -0.82
    軼
    -0.82
    ácidos
    -0.82
     reign
    -0.81
    abestanden
    -0.79
    POSITIVE LOGITS
     ambayo
    0.85
     baixar
    0.85
     Twenty
    0.82
    Twenty
    0.81
     aaa
    0.81
     setback
    0.79
    gem
    0.78
    ądz
    0.76
    Eleven
    0.75
     crin
    0.73
    Activations Density 0.060%

    No Known Activations