© 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. 82474
    Prev
    Next
    INDEX
    Explanations

    HTML attributes

    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
     Lef
    -0.86
    бурге
    -0.82
    ального
    -0.79
    硬
    -0.78
    momix
    -0.77
     secar
    -0.77
    owulf
    -0.76
    клопе
    -0.76
     Class
    -0.76
    似乎
    -0.75
    POSITIVE LOGITS
    size
    0.81
     dachte
    0.81
    児童
    0.81
     coke
    0.81
    合う
    0.79
     Rajiv
    0.79
    платье
    0.78
     clout
    0.77
    itní
    0.77
    fromLTRB
    0.77
    Activations Density 0.032%

    No Known Activations