© 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. 84591
    Prev
    Next
    INDEX
    Explanations

    free download or free service

    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
    жава
    -0.67
     Kamis
    -0.67
    דות
    -0.67
     Council
    -0.67
     Parad
    -0.64
     impreg
    -0.64
    Джерела
    -0.64
    奏
    -0.64
    Everton
    -0.63
    repe
    -0.63
    POSITIVE LOGITS
     Guyana
    0.78
    btnDelete
    0.71
    оте
    0.71
     Citi
    0.71
    eluarkan
    0.69
     mía
    0.69
     alumni
    0.69
     propias
    0.66
     dirname
    0.65
     aici
    0.65
    Activations Density 0.063%

    No Known Activations