© 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. 97812
    Prev
    Next
    INDEX
    Explanations

    key-value pairs

    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
    delsen
    -1.00
     londres
    -0.93
     Frankfurter
    -0.93
     commensurate
    -0.92
     Specifically
    -0.92
     fanns
    -0.92
     specific
    -0.91
     from
    -0.91
     mengalir
    -0.91
     terjun
    -0.91
    POSITIVE LOGITS
     старый
    1.06
    istocene
    0.98
    <bos>
    0.97
    香り
    0.94
     découvre
    0.90
    ossa
    0.89
     arquite
    0.88
    豪華
    0.88
    カッコ
    0.88
    壁紙
    0.88
    Activations Density 0.056%

    No Known Activations