© 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. 98740
    Prev
    Next
    INDEX
    Explanations

    songs, cases, or dates

    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
    __((
    -0.82
     grunge
    -0.80
     امريكا
    -0.76
     AIDS
    -0.75
    Grant
    -0.72
     Wines
    -0.71
    theria
    -0.70
     Rajiv
    -0.69
     دولار
    -0.69
     carcinoma
    -0.69
    POSITIVE LOGITS
     打
    0.94
     Iranian
    0.75
     Bic
    0.71
    Bic
    0.71
     ladr
    0.71
    confirmButton
    0.70
    乾隆
    0.68
     दी
    0.68
     disco
    0.68
     LED
    0.68
    Activations Density 0.153%

    No Known Activations