© 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. 93690
    Prev
    Next
    INDEX
    Explanations

    WS proxy or DataSource

    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
     силу
    -0.78
     åter
    -0.77
     sessionFactory
    -0.76
    場の
    -0.76
     Zamora
    -0.75
    炀
    -0.75
    war
    -0.74
    cocks
    -0.73
    町の
    -0.73
     $
    -0.73
    POSITIVE LOGITS
    难题
    0.80
    🧼
    0.80
    Lähde
    0.79
     fright
    0.73
    ,-\
    0.71
    دهم
    0.71
     победи
    0.69
    Dancing
    0.69
    Karim
    0.69
    atts
    0.68
    Activations Density 0.006%

    No Known Activations