© 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. 22-GEMMASCOPE-RES-131K
    7. 95839
    Prev
    Next
    INDEX
    Explanations

    weekly financial news

    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_22/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
    imentel
    -0.83
     както
    -0.81
     actes
    -0.80
     keren
    -0.80
     setContent
    -0.79
    ânea
    -0.78
    }.\
    -0.77
     erw
    -0.77
    chera
    -0.76
     Antenna
    -0.76
    POSITIVE LOGITS
    多く
    1.02
     präsenti
    0.91
    ắt
    0.88
    ATE
    0.84
    vané
    0.84
    zwald
    0.83
    ürü
    0.82
    تی
    0.81
     some
    0.81
     TLS
    0.81
    Activations Density 0.001%

    No Known Activations