© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 25718
    Prev
    Next
    INDEX
    Explanations

    national historical site, court papers, chief executive

    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
     Malaysia
    -0.82
    ਦੇ
    -0.78
     Kel
    -0.77
    اضر
    -0.75
     Malaysian
    -0.72
     Darn
    -0.72
     aire
    -0.71
     mando
    -0.70
     pottery
    -0.69
     bus
    -0.68
    POSITIVE LOGITS
    Xor
    0.78
    aaS
    0.75
    itrile
    0.73
     は
    0.71
     BOOST
    0.71
    Keterangan
    0.70
     tolerant
    0.70
     Penelitian
    0.70
    baka
    0.69
    Lips
    0.69
    Activations Density 0.019%

    No Known Activations