© 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. 38133
    Prev
    Next
    INDEX
    Explanations

    deep and following words

    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
    諳
    -0.88
     menjel
    -0.68
    ære
    -0.67
     mantle
    -0.66
    稱
    -0.65
     neonatal
    -0.65
     fény
    -0.65
     Niedersch
    -0.65
    THX
    -0.65
    Compra
    -0.64
    POSITIVE LOGITS
     handcu
    0.82
    oxid
    0.80
    Pune
    0.78
    浅
    0.75
    Lithuania
    0.73
     Ely
    0.72
     nostre
    0.70
     alley
    0.69
     donnant
    0.69
     meantime
    0.69
    Activations Density 0.028%

    No Known Activations