© 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. 107570
    Prev
    Next
    INDEX
    Explanations

    code snippets and measurements

    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
     Alpes
    -1.01
     pellic
    -0.94
    »;
    -0.93
    */),
    -0.89
     \"%
    -0.89
     nā
    -0.89
    '),
    -0.87
     Lombar
    -0.86
     Conci
    -0.86
    iteľ
    -0.85
    POSITIVE LOGITS
    encre
    0.90
     жк
    0.90
     Tinubu
    0.88
     modrá
    0.87
     Carl
    0.85
     answer
    0.84
     red
    0.83
     dâu
    0.82
     Independence
    0.81
    やった
    0.81
    Activations Density 0.000%

    No Known Activations