© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107201
    Prev
    Next
    INDEX
    Explanations

    titles and english technical phrases

    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
    ！！！
    -1.02
    ｗ
    -0.94
     by
    -0.94
    ～」
    -0.93
    ！！！！
    -0.93
    CharArray
    -0.93
    ！(
    -0.92
    家は
    -0.90
     semangat
    -0.88
    لاه
    -0.88
    POSITIVE LOGITS
     Communicate
    0.98
    throughout
    0.96
     nhung
    0.96
    begins
    0.91
     Geben
    0.91
     DURING
    0.88
    itur
    0.87
     pyta
    0.87
     Reverso
    0.87
    aucune
    0.87
    Activations Density 0.000%

    No Known Activations